skill-forge-evolve

A maintenance guide for improving existing Claude Code skills, which are reusable instructions that shape how the coding assistant handles tasks. It helps diagnose why a skill activates incorrectly or produces poor results.

In plain words
What is it for?
Use it to refine skill descriptions, add missing triggers or sub-skills, improve instructions and error handling, and adjust the skill's structure as requirements change.
Why use it?
It removes the guesswork from fixing skills that trigger too often, not often enough, stop early, give inconsistent results, or lack needed instructions.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/agricidaniel/skill-forge/skill-forge-evolve
Any agent
npx skills add AgriciDaniel/skill-forge --skill skill-forge-evolve
Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/skill-forge

Made for: Claude Code, Codex.

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,650 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00081 $0.01650
Opus 5 $0.00041 $0.00825
Sonnet 5 $0.00016 $0.00330
Haiku 4.5 $0.00008 $0.00165

Measured 3d ago against content hash 4b4cd835f010, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-forge-evolve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/skill-forge-evolve/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Evolution & Improvement

Process

Step 1: Diagnose the Issue

Ask the user or analyze logs to identify the problem category:

Category A: Triggering Issues

  • Under-triggering: Skill doesn't activate when it should
  • Over-triggering: Skill activates when it shouldn't
  • Mis-triggering: Wrong sub-skill activates

Category B: Execution Issues

  • Incomplete workflows: Skill stops before finishing
  • Incorrect output: Results don't match expectations
  • Missing error handling: Failures not handled gracefully
  • Performance: Too slow or too many token used

Category C: Architecture Issues

  • Missing capability: New use case not covered
  • Scale issues: Skill too large, needs decomposition
  • Cross-reference problems: Links to non-existent files

Category D: Quality Issues

  • Inconsistent results: Different outputs for same input
  • Vague instructions: Claude interprets differently each time
  • Missing examples: No concrete guidance

Step 2: Apply Fix by Category

Fix: Under-Triggering
  1. Read current description
  2. Identify missing trigger phrases
  3. Add domain keywords and paraphrases
  4. Add file type mentions if relevant
  5. Test with 5 queries that should now trigger

Common causes:

  • Description too generic
  • Missing common paraphrases
  • Technical jargon without lay terms

Fix template:

# Before (under-triggers)
description: Analyzes code quality

# After (specific triggers)
description: >
  Static code analysis and quality assessment. Checks code style,
  complexity, security vulnerabilities, and test coverage. Use when
  user says "code review", "code quality", "lint", "static analysis",
  "code smell", "code audit", or "check my code".
Fix: Over-Triggering
  1. Read current description
  2. Identify why unrelated queries trigger it
  3. Add negative triggers ("Do NOT use for...")
  4. Make description more specific
  5. Test with 5 queries that should NOT trigger

Fix template:

# Before (over-triggers)
description: Processes documents for review

# After (specific + negative triggers)
description: >
  Processes PDF legal documents for contract clause extraction and
  compliance review. Use for legal contracts, NDAs, terms of service.
  Do NOT use for general document editing, formatting, or non-legal PDFs.

Read the full file on GitHub · 232 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 232 lines · 81 tokens per session scan A 4b4cd835f010

Subscribe to this mod's changes

skill-forge-evolve is a skill published in the GitHub repository AgriciDaniel/skill-forge (166 stars, last pushed 4mo ago), licensed MIT. It adds 81 tokens to every session and 1,650 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

wiki-ingest

Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…

AgriciDaniel/claude-obsidian · 88 tokens

autoresearch

Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…

AgriciDaniel/claude-obsidian · 80 tokens

canvas

Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.

AgriciDaniel/claude-obsidian · 72 tokens

wiki-retrieve

Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…

AgriciDaniel/claude-obsidian · 81 tokens

wiki

Initialize, adopt, and route work for a separate Obsidian knowledge vault through the portable claude-obsidian core. Use for vault setup, scaffolding, workspace selection, cross-project configuration, or choosing the correct wiki sub-skill. Triggers: /wiki, set up wiki, scaffold vault, create knowledge base, adopt…

AgriciDaniel/claude-obsidian · 84 tokens

defuddle

Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.

AgriciDaniel/claude-obsidian · 57 tokens