Agent skill

Skillforge

A skill your agent uses when creating, improving, finding, or auditing agent skills - the user says 'create a skill', 'do I have a skill for X', 'improve the X skill', 'which skill should I use'…

MITAuto-check: notesAgent Workflows

Install Skillforge

skills CLI

$ npx skills add tripleyak/SkillForge --skill skillforge -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install tripleyak/SkillForge skillforge --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "skillforge" agent skill from https://github.com/tripleyak/SkillForge/tree/main into .claude/skills/skillforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skillforge", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add tripleyak/SkillForge --skill skillforge -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install tripleyak/SkillForge skillforge --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "skillforge" agent skill from https://github.com/tripleyak/SkillForge/tree/main into .agents/skills/skillforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skillforge", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add tripleyak/SkillForge --skill skillforge -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install tripleyak/SkillForge skillforge --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "skillforge" agent skill from https://github.com/tripleyak/SkillForge/tree/main into .cursor/skills/skillforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skillforge", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add tripleyak/SkillForge --skill skillforge -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install tripleyak/SkillForge skillforge --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "skillforge" agent skill from https://github.com/tripleyak/SkillForge/tree/main into .gemini/skills/skillforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skillforge", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install tripleyak/SkillForge skillforge

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add tripleyak/SkillForge --skill skillforge -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "skillforge" agent skill from https://github.com/tripleyak/SkillForge/tree/main into .github/skills/skillforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skillforge", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add tripleyak/SkillForge --skill skillforge -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install tripleyak/SkillForge skillforge --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "skillforge" agent skill from https://github.com/tripleyak/SkillForge/tree/main into .opencode/skills/skillforge/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skillforge", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: skillforge
GitHub stars: 905
Token cost: ~2.3k tokens
SKILL.md length: 883 words
Files: 86 (incl. scripts, references, assets)
Skills in repo: 1
Repo updated: Jul 29, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses when creating, improving, finding, or auditing agent skills - the user says 'create a skill', 'do I have a skill for X', 'improve the X skill', 'which skill should I use'…

Auditing agent skills - the user says create a skill
SKILL.md covers Routing (Phase 0), Creation pipeline, Frontmatter and platform facts and Ecosystem maintenance, plus 4 more sections
Calls python3 and codex
Do I have a skill for X

What it does

Skillforge is an agent skill from tripleyak/SkillForge. Use when creating, improving, finding, or auditing agent skills - the user says 'create a skill', 'do I have a skill for X', 'improve the X skill', 'which skill should I use', asks whether a skill exists for a task, or wants to validate, test, evaluate, package, or health-check skills. Also use for skill ecosystem maintenance (duplicate detection, stale skills, trigger collisions) and advisor checkpoints.

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 87 other files, including scripts, reference files and assets (for example `CONTEXT.md`, `README.md` and `SKILLFORGE_AUDIT.md`).

It sits in Agent Workflows, covering Skill authoring and LLM evaluation. The repository describes itself as: A skill creator that proves its skills work. Evidence-driven skill creation for Claude Code and Codex: baseline-tested generation, per-skill regression evals, ecosystem doctor… The licence is MIT.

When your agent uses it

Auditing agent skills - the user says create a skill
Do I have a skill for X
Improve the X skill
Which skill should I use

Example prompts

“create a skill”
“do I have a skill for X”
“improve the X skill”
“/skillforge”

Requirements

Python 3
Pre-approved tools (allowed-tools): Read, Glob, Grep, Bash, Write, Edit, Task

What it can do on your machine

Read from SKILL.md and the folder at commit 4fc8bb4. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- Read
- Glob
- Grep
- Bash
- Write
- Edit
- Task
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
- python3
- codex
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Skillforge loads about 2.3k tokens when it runs, and up to ~26k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 883 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~105
When it runs · the whole SKILL.md, loaded when a task matches: ~2.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~26k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
```
allowed-tools: Read, Glob, Grep, Bash, Write, Edit, Task
```

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from tripleyak/SkillForge at commit 4fc8bb4, republished under its MIT licence (© tripleyak). 883 words, ~2,290 tokens.

Download SKILL.mdSave it as .claude/skills/skillforge/SKILL.md (or your agent's skills folder). This skill also uses 85 other files; get the full folder from GitHub.

name: skillforge
description: Use when creating, improving, finding, or auditing agent skills - the user says 'create a skill', 'do I have a skill for X', 'improve the X skill', 'which skill should I use', asks whether a skill exists for a task, or wants to validate, test, evaluate, package, or health-check skills. Also use for skill ecosystem maintenance (duplicate detection, stale skills, trigger collisions) and advisor checkpoints.
allowed-tools: Read, Glob, Grep, Bash, Write, Edit, Task
license: MIT
user-invocable: true
metadata.version: 6.0.0
metadata.domains: meta-skill, skill-creation, skill-testing, orchestration, routing
metadata.type: orchestrator

SkillForge 6 - Skill Router, Creator & Ecosystem Maintainer

Routes any skill-related request to the right action (use, improve, create, compose), creates new skills through an evidence-driven pipeline, and maintains the health of the whole skill ecosystem. Core principle: skill quality is a property of behavior, not documents - a skill is done when a fresh agent demonstrably does better with it than without it.

Routing (Phase 0)

Always triage before creating anything:

bash

python3 scripts/discover_skills.py            # refresh index (auto-refreshes if >24h old)
python3 scripts/triage_skill_request.py "<the user's request>" --json

Triage result	Action
Strong match (existing skill)	Recommend it; do not create a duplicate
Moderate match	Offer IMPROVE_EXISTING on the matched skill
Weak/no match + create intent	Proceed to creation pipeline
Multi-domain	Suggest composing existing skills
Ambiguous	Ask one clarifying question

Match bands are keyword-evidence heuristics, not calibrated probabilities - report them as "strong/moderate/weak match", never as percent confidence.

Creation pipeline

Run phases in order. Each phase's detailed procedure lives in its reference - read the reference when you reach the phase, not before.

0. Baseline gate (RED). Before designing anything, dispatch a fresh subagent (Task tool) on 1-2 representative target tasks WITHOUT the skill. Capture verbatim what it does wrong. If the baseline does not fail, stop - the skill is unnecessary. The failures become the skill's test cases and its description keywords. See references/testing-and-evals.md.

1. Analysis. Identify explicit, implicit, and discovered requirements. Apply the three load-bearing lenses - Inversion (what guarantees failure → anti-patterns), Pareto (which 20% of scope delivers 80% → cut the rest), Root Cause (is this the real problem?) - plus any others from references/multi-lens-framework.md that earn their tokens. Classify the failure type you are guarding against and match the guidance form to it (see the failure-form table in references/testing-and-evals.md). Choose instruction specificity with references/degrees-of-freedom.md. Decide scripts with references/script-integration-framework.md.

2. Specification. Write the spec using references/specification-template.md. Minimal tier (problem, requirements, decisions with WHY, success criteria, test scenarios) for most skills; full tier (temporal projection, obsolescence triggers, extension points) only for infrastructure skills. Never fill a section you cannot ground - omit it.

3. Generation in fresh context. Dispatch a subagent (Task tool) that receives ONLY the spec and the baseline failures - not the analysis transcript - to write SKILL.md and supporting files. Scaffold first: python3 scripts/init_skill.py <name> --path <skills-dir>. Description doctrine: trigger conditions only, third person, symptom keywords, never a workflow summary. Budget: SKILL.md under 1,500 words; move depth to references/; <details> tags save zero tokens for agents - do not use them.

4. Execution testing (GREEN). Re-run the baseline tasks WITH the skill via fresh subagents. Gate on behavioral delta: the with-skill runs must not exhibit the baseline failures. Then run the description-triggering check (positive and near-miss queries). Iterate description and body against observed failures, not hunches. For improvements to existing skills, use blind A/B judging. Full protocols: references/testing-and-evals.md.

5. Review = lint + one adversarial reviewer. Mechanical gates first:

bash

python3 scripts/validate_skill.py <skill-dir>     # structure, frontmatter, lint (pinned models, word budget, description shape)
python3 scripts/check_docs_safety.py <skill-dir>

Then one fresh-context subagent prompted to REFUTE the skill (find the case where it misleads, over-triggers, or fails its own scenarios), carrying the reviewer checklists in references/synthesis-protocol.md. Fix what it proves; ship what survives. Do not convene approval panels - same-model unanimity measures nothing.

6. Ship with evals. Every generated skill keeps its tests: an evals/ directory (trigger queries + behavioral scenarios + assertions) so future edits can be regression-tested with python3 scripts/run_skill_evals.py <skill-dir>. Iterate post-ship with references/iteration-guide.md.

Show full SKILL.md (355 more words)Show less

Frontmatter and platform facts

Write frontmatter against the current Claude Code field set (17 fields) documented in references/claude-code-frontmatter.md, which also covers hooks (hooks receive JSON on stdin, not env vars), context: fork/agent, $ARGUMENTS, and the agentskills.io portability limits (64-char name, 1024-char description) that validate_skill.py enforces. Never pin dated model IDs (claude-*-YYYYMMDD) - the validator rejects them.

Ecosystem maintenance

bash

python3 scripts/skillforge_doctor.py              # trigger collisions, duplicates, stale refs, token budgets, description lint
python3 scripts/compile_skill.py <dir> --target claude|codex|agentskills
python3 scripts/package_skill.py <dir> ./dist     # .skill zip, honors .skillignore
python3 scripts/mine_skill_friction.py --consent  # opt-in: mine local transcripts for skill friction

Use doctor output to drive IMPROVE_EXISTING work; use friction reports as advisor evidence.

Context Skill Advisor

Proactive suggestions are delivered through Claude Code hooks (SessionStart surfaces the queue; UserPromptSubmit scores checkpoints inline) - no daemon. Configure with python3 scripts/install_skillforge.py (interactive; hooks and Personal Context scanning are opt-in, never default). Manage the queue: python3 scripts/context_advisor.py list|use|snooze|dismiss. Suggestions are evidence-backed and never auto-invoke a skill.

Script inventory

Script	Purpose
`discover_skills.py`	Build/refresh the cross-runtime skill index
`triage_skill_request.py`	Route input to use/improve/create/compose/clarify
`validate_skill.py`	Full structural + lint validation (`quick_validate.py` = fast subset)
`run_skill_evals.py`	Run a skill's evals/ regression suite
`skillforge_doctor.py`	Ecosystem health report
`init_skill.py`	Scaffold a new skill (with evals/)
`compile_skill.py`	Compile a skill for a target runtime
`package_skill.py`	Package as .skill archive
`mine_skill_friction.py`	Opt-in transcript friction mining
`context_advisor.py` / `install_skillforge.py`	Advisor queue and setup
`check_docs_safety.py`	Unsafe interpolation check

Script exit codes: 0 success, 1 failure, 2 usage/consent error, 10 validation failure, 11 verification/dependency failure.

Extension points: new lint checks in validate_skill.py; new doctor checks in skillforge_doctor.py; new compile targets in compile_skill.py; new lenses in references/multi-lens-framework.md.

Anti-patterns

Avoid	Instead
Creating without a failing baseline	Run the RED gate; no failure = no skill
Description that summarizes workflow	Trigger conditions only - agents act on summaries and skip the body
Body "Triggers" sections as a mechanism	Only the frontmatter description drives invocation
Approval panels and self-scored gates	Lint what is falsifiable; adversarially refute the rest
`<details>` blocks for "progressive disclosure"	Separate reference files loaded on demand
Pinned dated model IDs	Family aliases or omit `model:`
Duplicating an existing skill	Phase 0 triage first, always

Verification checklist

Baseline failure captured before writing (RED)
With-skill runs clear the baseline failures (GREEN)
Trigger check passes on positive and near-miss queries
validate_skill.py and check_docs_safety.py pass
Adversarial reviewer's proven issues fixed
evals/ shipped with the skill; run_skill_evals.py passes
SKILL.md under 1,500 words (wc -w)

Files

SKILL.md and 85 other files (scripts, references, assets) in the repository root of tripleyak/SkillForge.

SKILL.md
.gitignore
.skillignore
CONTEXT.md
LICENSE
README.md
SKILLFORGE_AUDIT.md
assets/images/01-title.png
assets/images/02-quality-gap.png
assets/images/03-quality-built-in.png
assets/images/04-four-phase-architecture.png
assets/images/05-phase1-thinking-lenses.png
assets/images/06-phases-2-3.png
assets/images/07-phase4-synthesis.png
assets/images/08-evolution-mandate.png
assets/images/09-core-principles.png
assets/images/10-agentic-capabilities.png
assets/images/11-directory-structure.png
assets/images/12-installation.png
… and 67 more

Open the folder on GitHubat commit 4fc8bb4

Compare with similar skills

Skillforge next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Skillforge compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Skillforge this skilltripleyak/SkillForge	905	—	~2.3k	Automated safety check: Notes	MIT	2 mo ago
Create Skilldavekilleen/Dex	493	—	~2.9k	Automated safety check: Pass	Custom licence	5 days ago
Author Skillericrisco/rsc-harness	156	—	~4.3k	Automated safety check: Pass	MIT	yesterday
Skill CreatorAzure/azqr	794	89 repos	~8.2k	Automated safety check: Pass	Apache-2.0	2 days ago
Zach Seller Skill Creatorzach22-1999/amazon-skills	206	1 repos	~3.9k	Automated safety check: Pass	Apache-2.0	1 mo ago
Skill CreatorAgentTeam-TaichuAI/ScienceClaw	670	—	~10k	Automated safety check: Pass	Apache-2.0	5 mo ago

Similar skills

Create Skill
davekilleen/Dex
Author a new Dex skill that actually fires and passes the quality bar.
493 GitHub stars~2.9k tokensUpdated 5 days ago
Agent WorkflowsAuto-check passed
Author Skill
ericrisco/rsc-harness
A skill your agent uses when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into…
156 GitHub stars~4.3k tokensUpdated yesterday
Agent WorkflowsAuto-check passed
Skill Creator
Azure/azqr
Official
Create new skills, modify and improve existing skills, and measure skill performance.
794 GitHub starsUsed in 89 repos~8.2k tokens
Agent WorkflowsAuto-check passed
Zach Seller Skill Creator
zach22-1999/amazon-skills
亚马逊卖家专用的 skill 创建器（中文）。当用户想把一个亚马逊运营/自媒体/日常工作流程变成可复用的 skill 时使用。触发场景包括但不限于：用户说"我想做一个 skill""把这个流程变成 skill""帮我写个自动化""优化我已有的 skill""给这个工作流做个自动化"，即使用户没用"skill"这个词，只要在描述"以后每次都这样做"的重复性工作时也应触发。本 skill…
206 GitHub starsUsed in 1 repo~3.9k tokens
Agent WorkflowsAuto-check passed
Skill Creator
AgentTeam-TaichuAI/ScienceClaw
Create new skills, modify and improve existing skills, and measure skill performance.
670 GitHub stars~10k tokensUpdated 5 mo ago
Agent WorkflowsAuto-check passed
Skill Creator
luongnv89/asm
Create a skill or bring an existing one up to the same standard (validate + asm eval fix loop); run evals, tune triggering.
953 GitHub stars~5.3k tokensUpdated yesterday
Agent WorkflowsAuto-check passed

Questions about Skillforge

What does Skillforge do?

A skill your agent uses when creating, improving, finding, or auditing agent skills - the user says 'create a skill', 'do I have a skill for X', 'improve the X skill', 'which skill should I use'…. Skillforge is an agent skill from tripleyak/SkillForge. Use when creating, improving, finding, or auditing agent skills - the user says 'create a skill', 'do I have a skill for X', 'improve the X skill', 'which skill should I use', asks whether a skill exists for a task, or wants to validate, test, evaluate, package, or health-check skills.

When should I use Skillforge?

Skillforge fits situations like: auditing agent skills - the user says create a skill; do I have a skill for X; improve the X skill; which skill should I use.

How do I install Skillforge in Claude Code?

Run `npx skills add tripleyak/SkillForge --skill skillforge -a claude-code`. Or copy the skill folder (the tripleyak/SkillForge repository) into .claude/skills/skillforge in your project. Claude Code loads it when a task matches its description.

How do I install Skillforge in Codex?

Run `npx skills add tripleyak/SkillForge --skill skillforge -a codex`. Or copy the skill folder (the tripleyak/SkillForge repository) into .agents/skills/skillforge in your project. Codex loads it when a task matches its description.

Can I use Skillforge in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tripleyak/SkillForge --skill skillforge -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skillforge, .gemini/skills/skillforge, .github/skills/skillforge and .opencode/skills/skillforge in your project.

What does Skillforge need to run?

Going by SKILL.md and its folder, Skillforge needs the command-line tools its instructions call (python3 and codex). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Glob, Grep, Bash, Write, Edit, Task.

Does Skillforge access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Skillforge safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Skillforge use?

Skillforge is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Skillforge use?

About 2.3k tokens (SKILL.md is roughly 9.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 23k tokens, read only when the agent opens those files.

What are the alternatives to Skillforge?

Skills that share tags, products or a category with Skillforge: Create Skill (davekilleen/Dex, 493 stars), Author Skill (ericrisco/rsc-harness, 156 stars), Skill Creator (Azure/azqr, 794 stars) and Zach Seller Skill Creator (zach22-1999/amazon-skills, 206 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skillforge?

tripleyak (a GitHub user) maintains it in tripleyak/SkillForge, which has 905 GitHub stars. The repository was last updated on July 29, 2026.

Source: tripleyak/SkillForge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Skillforge

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

SkillForge 6 - Skill Router, Creator & Ecosystem Maintainer

Routing (Phase 0)

Creation pipeline

Frontmatter and platform facts

Ecosystem maintenance

Context Skill Advisor

Script inventory

Anti-patterns

Verification checklist

Files

Compare with similar skills

Similar skills

Create Skill

Author Skill

Skill Creator

Zach Seller Skill Creator

Skill Creator

Skill Creator

Related

Questions about Skillforge