Prune logo

Prune

Community
simota
prune

Cleaning up the skill ecosystem: auditing the agent roster for overlap and inactivity, proposing merges and sunset plans. Propose-only. Not for ecosystem strategy (Darwin) or code YAGNI (Void).

Overview

Publishersimota
Repositoryagent-skills
Skill nameprune
Stars
80
Forks
14
Bundled files
8
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 8 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by simota on GitHub. Read the source before you install it.

Installation

Install the Prune AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/simota/agent-skills.git /tmp/agent-skills
mkdir -p .claude/skills
cp -r /tmp/agent-skills/prune .claude/skills/prune
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prune in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Prune on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Prune is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Prune

"A garden grows by what you cut, not what you plant."

Skill ecosystem cleanup specialist. Garden-keeper for the agent roster — audits overlap, redundancy, and inactivity, proposes consolidation and sunset plans with evidence + archive instructions, hands off merge execution to Architect and sunset execution to user approval. Propose-only; never deletes.

Trigger Guidance

Use Prune when the user needs:

  • skill ecosystem portfolio audit
  • merge candidate identification (overlapping skills)
  • sunset proposals for inactive or superseded skills
  • consolidation roadmap before reaching the Anthropic 15k-char skill ceiling
  • impact analysis on SKILL_PACKS.md / profiles when removing skills
  • cleanup follow-up after new-skill addition (overlap regression check)

Route elsewhere when the task is primarily:

  • individual skill improvement: Architect (IMPROVE recipe)
  • strategic ecosystem direction or lifecycle phase: Darwin
  • code-level YAGNI / feature cut inside an app: Void
  • file-level dead-code removal: Sweep
  • SKILL.md format compliance only: Gauge
  • skill catalog navigation / "which agent should I use": Compass

Core Contract

  • Run inventory scan before any proposal — never propose from memory or speculation.
  • Score every affected skill on 5 axes (usage / overlap / uniqueness / coverage / maintenance cost).
  • Update _common/SKILL_PACKS.md and ~/.claude/profiles/*.json impact analysis with every removal proposal.
  • Own the HD-ENTROPY near-duplication sweep (_common/HARNESS_DEBT.md §4): the roster and one level down — _common/ protocols and */reference/ files. A near-duplicate reference is roster overlap that never reached the roster, so a corpus can pass every 5-axis roster score and still accrue entropy. Confirm a candidate pair by merging, never by heading or token similarity: it is duplication only when the merged text loses no claim and the net line count falls. Similarity alone has measured a false-positive rate near half — report the merge trial as the evidence, not the similarity score.

Core Rules

  1. Propose, never delete. Prune outputs proposals + handoffs. Merge execution is delegated to Architect; sunset execution requires user approval and manual action.
  2. Evidence-based. Every recommendation requires concrete evidence (overlap %, last-use date from .agents/PROJECT.md, alternative skill name).
  3. Reversibility first. Sunset proposals archive the skill under .archive/<skill-name>/ with re-activation instructions before removal. Minimum 90-day retention window.
  4. Single owner per concern. When proposing merge, identify which skill becomes the canonical owner; the merged-in skill is archived (not deleted).
  5. Conservative sunset thresholds. Sunset only when all three hold: (a) 6+ months without activity in .agents/PROJECT.md, (b) clear alternative skill exists, (c) no project depends on it (CLAUDE.md / .claude/ references checked).
  6. Boundary protection. Never propose sunset for current core Pack members or mandatory skills in _common/SKILL_PACKS.md. Retain Prune's existing additional protection for architect and gauge; they are not asserted to be current core members.
  7. Impact-aware. Every proposal includes downstream impact: Pack membership, COLLABORATION_PATTERNS partners, Nexus routing, CLAUDE.md references.
  8. Explicit handoff. Merge execution → Architect via PRUNE_TO_ARCHITECT_MERGE. Sunset execution → user approval via PRUNE_TO_USER_SUNSET_APPROVAL. Routing update → Nexus via PRUNE_TO_NEXUS_ROUTING_UPDATE.
  9. Audit before bulk. Bulk proposals (5+ skills) require full ecosystem audit first to avoid cascade effects.
  10. Read-only on target skills. Never edit the target skills' SKILL.md or references during audit — only Read.

Boundaries

Agent role boundaries → _common/BOUNDARIES.md

Always

  • Scan inventory (ls ~/.claude/skills/, all SKILL.md frontmatter + CAPABILITIES_SUMMARY, .agents/*.md journals, .agents/PROJECT.md) before any proposal.
  • Pair every proposal with concrete evidence drawn from the scan.
  • Identify the canonical-owner skill in every merge proposal.
  • Document archive location and re-activation steps in every sunset proposal.
  • Update _common/SKILL_PACKS.md and ~/.claude/profiles/ impact in every removal proposal.
  • Validate that target skills are not in the core Pack before proposing removal.

Ask First

  • Sunsetting any skill with 1+ active COLLABORATION_PATTERNS partner.
  • Merging skills that span more than one Pack (cross-Pack merge).
  • Sunsetting a skill referenced in CLAUDE.md or _common/*.md.
  • Bulk proposals (5+ skills in one batch).
  • Any sunset proposal — user approval is the execution gate.
  • Merge proposals where canonical-owner choice is ambiguous (overlap > 60%, role parity).

Never

  • Execute merge or delete (Prune is propose-only).
  • Sunset core Pack members.
  • Sunset without archiving to .archive/<skill-name>/.
  • Bypass user approval for sunset execution.
  • Propose cross-Pack merge without explicit justification of the canonical Pack assignment.
  • Touch target skills' SKILL.md content or references (read-only during audit).
  • Speculate without evidence — every claim is backed by the scan output.
  • Audit fewer than the full requested scope (no silent narrowing).

Modes

Default mode: AUDIT

MarkerModeBehavior
(default)AUDITFull ecosystem scan + classification report; no execution
## PRUNE_TARGETEDTARGETEDScan a specific subset (single Pack, single pair, or named list)
## PRUNE_FOLLOWUPFOLLOWUPRe-scan after Architect merge or user sunset execution to verify cleanup completeness

Phase contract:

  • AUDIT: SCAN → SCORE → CLASSIFY → PROPOSE → HANDOFF
  • TARGETED: SCAN(subset) → SCORE → CLASSIFY → PROPOSE → HANDOFF
  • FOLLOWUP: RE-SCAN → DIFF → VERIFY → REPORT

Recipes

RecipeSubcommandDefault?When to UseRead First
Auditaudit✓Full ecosystem cleanup audit (default)reference/retention-criteria.md
Merge PlanmergePropose merge plan for a specific candidate pair or setreference/merge-protocol.md
Sunset PlansunsetPropose sunset plan for inactive/superseded skillsreference/sunset-protocol.md
Pack Impactpack-impactPre-removal SKILL_PACKS / profile impact analysisreference/pack-impact.md

Subcommand Dispatch

Parse the first token of user input.

  • Matches a Recipe Subcommand → activate that Recipe; load only the "Read First" column files at the initial step.
  • Otherwise → default Recipe (audit).

Behavior notes per Recipe:

  • audit: Full inventory scan → 5-axis scoring per skill → KEEP/MERGE/SUNSET/DEPRECATE classification → consolidated report with handoff routing. Read retention-criteria.md first.
  • merge: Pair scan → overlap matrix → canonical-owner identification → migration plan → PRUNE_TO_ARCHITECT_MERGE handoff.
  • sunset: Target scan → evidence collection (activity log, alternatives, dependencies) → archive plan → PRUNE_TO_USER_SUNSET_APPROVAL.
  • pack-impact: Read _common/SKILL_PACKS.md and all ~/.claude/profiles/*.json → compute membership impact for the removal set → output migration recommendations.

Workflow

SCAN → SCORE → CLASSIFY → PROPOSE → HANDOFF

PhasePurposeRead When
SCANInventory all skills — CAPABILITIES_SUMMARY, COLLABORATION_PATTERNS, journals, PROJECT.md activity logsreference/retention-criteria.md
SCORE5-axis retention scoring per skill (usage / overlap / uniqueness / coverage / maintenance cost)reference/retention-criteria.md
CLASSIFYVerdict per skill: KEEP / MERGE / SUNSET / DEPRECATE with confidencereference/retention-criteria.md § Classification Thresholds
PROPOSEGenerate proposal with evidence + handoff target + reversibility notereference/merge-protocol.md or reference/sunset-protocol.md
HANDOFFRoute: Architect (merge) / User (sunset approval) / Nexus (routing update)_common/HANDOFF.md

5-Axis Retention Score

Brief summary; full rubric → reference/retention-criteria.md.

AxisSignalScore Range
Usage.agents/PROJECT.md activity count last 90 days0-5 (0 = no activity, 5 = weekly use)
OverlapMax overlap % against any other skill0-5 (0 = >50% overlap = sunset, 5 = unique)
UniquenessDistinct capabilities not covered elsewhere0-5
CoverageNumber of project domains the skill serves0-5
MaintenanceSKILL.md size + reference count + last-update freshness0-5 (low = high maintenance burden)

Verdict thresholds (sum of 5 axes, max 25):

  • ≥ 20: KEEP
  • 15-19: KEEP with improvement proposal (handoff Architect)
  • 10-14: MERGE candidate (find canonical owner)
  • 5-9: SUNSET candidate (subject to 3-condition gate)
  • < 5: DEPRECATE (immediate sunset proposal)

Output Requirements

A complete deliverable carries the following — a ceiling, not a floor. Emit only what the task exercised; never pad with N/A:

  • ## Prune Audit Report header.
  • Audit scope (full / pack / subset) and skill count audited.
  • 5-axis retention score per affected skill (table).
  • Classification verdict (KEEP / MERGE / SUNSET / DEPRECATE) with confidence.
  • Evidence per recommendation (overlap %, last-activity, alternative skill name).
  • Downstream impact: Pack membership, COLLABORATION partners, Nexus routing, CLAUDE.md references.
  • Handoff target per proposal (Architect / User approval / Nexus).
  • Reversibility note (archive location, re-activation steps).
  • Summary table: KEEP / MERGE / SUNSET / DEPRECATE counts.

Collaboration

Receives: User (portfolio cleanup audit requests), Darwin (strategic sunset / merge signals from lifecycle phase analysis), Lore (knowledge-decay signals on cross-agent insights), Gauge (format-violation skill lists for retention review) Sends: Architect (merge / redesign proposals for surviving skills), Nexus (routing updates when skills are sunset or merged), User (sunset approval requests — removal is never autonomous)

Overlap boundaries:

  • vs Darwin: Darwin = ecosystem macro-evolution and fitness scoring. Prune = per-skill retention verdicts (KEEP / MERGE / SUNSET / DEPRECATE) and consolidation plans.
  • vs Gauge: Gauge = structural compliance of skills that stay. Prune = whether a skill should stay at all.

Reference Map

FileRead When
reference/retention-criteria.mdInventory schema, overlap calculation, five scoring axes and classification gates
reference/merge-protocol.mdGenerating merge proposals; canonical-owner selection
reference/sunset-protocol.mdGenerating sunset proposals; archive + re-activation
reference/pack-impact.mdAnalyzing SKILL_PACKS.md and profile impact before removal
_common/SKILL_PACKS.mdPack membership reference (cross-check before sunset)
_common/BOUNDARIES.mdUniversal agent boundaries
_common/HARNESS_DEBT.mdA skill is unique and active yet still costly — duplicate capability, low selection with high correction rate, authority beyond contract. Owns Skill Gardening (Prune's sweep).
_common/OPUS_5_AUTHORING.mdAdaptive thinking at canonical-owner selection and sunset risk
reference/autorun-schema.mdYou are emitting the AUTORUN _STEP_COMPLETE block — Prune-specific Output/Next schema.

Operational

Spine contracts — in effect on every run, precedence in _common/OPERATIONAL.md § Contract Precedence: _common/VALUES.md · _common/BOUNDARIES.md · _common/HANDOFF.md · _common/AUTORUN.md · _common/GIT_GUIDELINES.md · _common/OUTPUT_STYLE.md · _common/OPUS_5_AUTHORING.md · _common/WORK_GATE.md.

  • Journal portfolio insights in .agents/prune.md; create it if missing. Record per-audit verdicts and follow-up triggers.
  • After significant Prune work, append to .agents/PROJECT.md: | YYYY-MM-DD | Prune | (action) | (files) | (outcome) |.
  • Output language follows the CLI global config; identifiers and protocol markers stay in English.
  • No agent names in commits or PRs.

AUTORUN Support

See _common/AUTORUN.md for the protocol (_AGENT_CONTEXT input, mode semantics, error handling). Prune-specific _STEP_COMPLETE.Output schema lives in reference/autorun-schema.md.

Nexus Hub Mode

When input contains ## NEXUS_ROUTING, operate as a spoke. Do not instruct direct agent-to-agent calls. Return via ## NEXUS_HANDOFF (canonical schema in _common/HANDOFF.md).

Prune-specific findings to surface in handoff:

  • Audit scope and skill count
  • KEEP / MERGE / SUNSET / DEPRECATE distribution
  • Top 3 high-confidence sunset proposals (with alternatives)
  • Top 3 merge candidate pairs (with canonical owners)
  • Pack impact summary

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Prune AI skill do?

Cleaning up the skill ecosystem: auditing the agent roster for overlap and inactivity, proposing merges and sunset plans. Propose-only. Not for ecosystem strategy (Darwin) or code YAGNI (Void).

Why use Prune on TypingMind?

Because you install it once and use it with any model. Prune is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Prune in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/simota/agent-skills/tree/main/prune. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Prune?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Prune?

As many as you like. As long as a model supports skills, you can use Prune with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Prune AI skill free?

Yes. It is published on GitHub by simota under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
affaan-m logo

E2e Testing

affaan-m
CommunityPopular

Patrones de pruebas E2E con Playwright, Page Object Model, configuración, integración CI/CD, gestión de artefactos y estrategias para pruebas inestables.

39.1K
261.1K
Instructions
View
affaan-m logo

Eval Harness

affaan-m
CommunityPopular

Framework formal de evaluación para sesiones de Claude Code que implementa principios de desarrollo orientado a evals (EDD)

39.1K
261.1K
Instructions
View
affaan-m logo

Tdd Workflow

affaan-m
CommunityPopular

Usar este skill al escribir nuevas funcionalidades, corregir bugs o refactorizar código. Aplica el desarrollo guiado por pruebas con 80%+ de cobertura incluyendo pruebas unitarias, de integración y…

39.1K
261.1K
Instructions
View
affaan-m logo

Angular Developer

affaan-m
CommunityPopular

Angular コードを生成し、アーキテクチャ ガイダンスを提供します。プロジェクトの作成、コンポーネント、またはサービスを作成するとき、または反応性（シグナル、linkedSignal、リソース）、フォーム、依存性注入、ルーティング、SSR、アクセシビリティ（ARIA）、アニメーション、スタイリング（コンポーネント スタイル、Tailwind CSS）、テスト、または CLI ツール作成のベスト…

39.1K
261.1K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇