Darwin Skill Optimizer
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
Implement the approved fixes from the action plan and log all changes.
$ npx skills add kayba-ai/agentic-context-engine --skill kayba-stage-7-fixer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kayba-ai/agentic-context-engine kayba-stage-7-fixer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/kayba-ai/agentic-context-engine.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/kayba-pipeline/stage-7-fixer .claude/skills/kayba-stage-7-fixer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "kayba-stage-7-fixer" agent skill from https://github.com/kayba-ai/agentic-context-engine/tree/main/.claude/skills/kayba-pipeline/stage-7-fixer into .claude/skills/kayba-stage-7-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kayba-stage-7-fixer", 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.
$skill-installer install https://github.com/kayba-ai/agentic-context-engine/tree/main/.claude/skills/kayba-pipeline/stage-7-fixerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add kayba-ai/agentic-context-engine --skill kayba-stage-7-fixer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kayba-ai/agentic-context-engine kayba-stage-7-fixer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kayba-ai/agentic-context-engine.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/kayba-pipeline/stage-7-fixer .agents/skills/kayba-stage-7-fixer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "kayba-stage-7-fixer" agent skill from https://github.com/kayba-ai/agentic-context-engine/tree/main/.claude/skills/kayba-pipeline/stage-7-fixer into .agents/skills/kayba-stage-7-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kayba-stage-7-fixer", 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.
$ npx skills add kayba-ai/agentic-context-engine --skill kayba-stage-7-fixer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kayba-ai/agentic-context-engine kayba-stage-7-fixer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kayba-ai/agentic-context-engine.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/kayba-pipeline/stage-7-fixer .cursor/skills/kayba-stage-7-fixer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "kayba-stage-7-fixer" agent skill from https://github.com/kayba-ai/agentic-context-engine/tree/main/.claude/skills/kayba-pipeline/stage-7-fixer into .cursor/skills/kayba-stage-7-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kayba-stage-7-fixer", 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.
$ gemini skills install https://github.com/kayba-ai/agentic-context-engine.git --path .claude/skills/kayba-pipeline/stage-7-fixer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add kayba-ai/agentic-context-engine --skill kayba-stage-7-fixer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kayba-ai/agentic-context-engine kayba-stage-7-fixer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kayba-ai/agentic-context-engine.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/kayba-pipeline/stage-7-fixer .gemini/skills/kayba-stage-7-fixer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "kayba-stage-7-fixer" agent skill from https://github.com/kayba-ai/agentic-context-engine/tree/main/.claude/skills/kayba-pipeline/stage-7-fixer into .gemini/skills/kayba-stage-7-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kayba-stage-7-fixer", 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.
$ gh skill install kayba-ai/agentic-context-engine kayba-stage-7-fixerInstalls 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).
$ npx skills add kayba-ai/agentic-context-engine --skill kayba-stage-7-fixer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kayba-ai/agentic-context-engine.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/kayba-pipeline/stage-7-fixer .github/skills/kayba-stage-7-fixer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "kayba-stage-7-fixer" agent skill from https://github.com/kayba-ai/agentic-context-engine/tree/main/.claude/skills/kayba-pipeline/stage-7-fixer into .github/skills/kayba-stage-7-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kayba-stage-7-fixer", 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.
$ npx skills add kayba-ai/agentic-context-engine --skill kayba-stage-7-fixer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kayba-ai/agentic-context-engine kayba-stage-7-fixer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kayba-ai/agentic-context-engine.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/kayba-pipeline/stage-7-fixer .opencode/skills/kayba-stage-7-fixer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "kayba-stage-7-fixer" agent skill from https://github.com/kayba-ai/agentic-context-engine/tree/main/.claude/skills/kayba-pipeline/stage-7-fixer into .opencode/skills/kayba-stage-7-fixer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kayba-stage-7-fixer", 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.
kayba-stage-7-fixerImplement the approved fixes from the action plan and log all changes.
Kayba Stage 7 Fixer is an agent skill from kayba-ai/agentic-context-engine. Implement the approved fixes from the action plan and log all changes. Trigger when the user says "run stage 7", "implement fixes", "apply action plan", or when invoked by the kayba-pipeline orchestrator. Requires eval/actionplan.md to exist.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows. It works with Git. The repository describes itself as: 🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit 3a31983. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
gitpythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Kayba Stage 7 Fixer loads about 1.8k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 790 words of instructions outside code blocks.
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.
The automated check found no risky patterns in SKILL.md.
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); files beside SKILL.md are not scanned.
The full file from kayba-ai/agentic-context-engine at commit 3a31983, republished under its Apache-2.0 licence (© kayba-ai). 790 words, ~1,846 tokens.
.claude/skills/kayba-stage-7-fixer/SKILL.md (or your agent's skills folder).Implement every non-discarded fix from the approved action plan.
eval/action_plan.md -- the approved action plan from Stage 5 (possibly modified during HITL in Stage 6)eval/stage6_decision.md -- if it exists, the HITL decision record from Stage 6 (contains user modifications)eval/baseline_metrics.json -- the pre-fix baseline metrics from Stage 3 (for reference in changes log)Read the action plan and stage6 decision (if present) before starting.
Before making ANY changes to source files:
git status to confirm the working tree stategit stash push -m "pre-pipeline-fixes-$(date +%Y%m%d-%H%M%S)"git tag pre-pipeline-fixes-$(date +%Y%m%d-%H%M%S)eval/changes_log.md under a "Rollback" section so the user can restore if neededThis ensures every fix is reversible with a single git stash pop or git checkout.
If eval/stage6_decision.md exists:
HITL_MODIFIED_IDS -- the insight/skill IDs that the user changed[HITL-MODIFIED] in the changes log so reviewers know which fixes reflect user judgment vs. the original pipeline outputIf the file does not exist, assume no HITL modifications were made.
Before implementing any fixes, scan the action plan for potential conflicts:
file_path -> [fix IDs that touch it]eval/changes_log.md under a "Conflict Notes" sectionWork through the action plan in priority order. For each non-discarded fix:
For code fixes:
For prompt fixes:
Append to eval/changes_log.md:
## Fix N: [skill/insight name] [HITL-MODIFIED if applicable]
**Type:** code fix | prompt fix
**Verdict from action plan:** [quote the recommendation]
**Files modified:**
- `path/to/file.py` -- [what changed and why]
**Before:**
\```
[relevant snippet before change]
\```
**After:**
\```
[relevant snippet after change]
\```
**Linked metrics:** [which metrics this should improve]
**Conflict notes:** [if this fix overlapped with another, note it here; otherwise "none"]If a fix requires changes you are unsure about:
NEEDS REVIEW in the changes log with:Do NOT re-run compute_baselines.py as part of this stage. The baseline metrics were computed against the original traces, which reflect old agent behavior. Re-running against the same traces will show zero movement for prompt-only fixes and is misleading.
Instead, after all fixes are applied, include a Next Steps section in the changes log that tells the user:
python eval/compute_baselines.py --traces-dir <new_traces_folder> --output eval/post_fix_metrics.jsoneval/post_fix_metrics.json against eval/baseline_metrics.json to measure actual improvementeval/changes_log.md as the primary outputeval/compute_baselines.py -- baselines should only be re-computed after new traces are generated with the updated agentWrite eval/changes_log.md:
# Changes Log
## Rollback
- **Safety ref:** `git stash` ref or tag name
- **To undo all fixes:** `git stash pop` or `git checkout <tag>`
## Conflict Notes
- [any file/region conflicts detected, or "No conflicts detected"]
## Summary
- Code fixes applied: N
- Prompt fixes applied: M
- Skipped / needs review: K
- HITL-modified items: J
---
## Fix 1: [skill name]
...
## Fix 2: [skill name]
...
---
## Needs Review
[Collected list of all NEEDS REVIEW items with context, or "None -- all fixes applied successfully"]
For each NEEDS REVIEW item:
- **Fix N: [skill name]**
- **What is unclear:** [specific ambiguity]
- **What would resolve it:** [information needed]
- **Files examined:** [paths and lines]
---
## Next Steps
To measure actual improvement:
1. Generate new traces by running the agent with the updated prompts/code
2. Re-run baselines:
\```bash
python eval/compute_baselines.py --traces-dir <new_traces_folder> --output eval/post_fix_metrics.json
\```
3. Compare `eval/post_fix_metrics.json` against `eval/baseline_metrics.json` to measure metric deltaseval/changes_log.md -- full log of all changes, conflicts, NEEDS REVIEW items, and next steps© kayba-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .claude/skills/kayba-pipeline/stage-7-fixer of kayba-ai/agentic-context-engine.
Open the folder on GitHubat commit 3a31983
Kayba Stage 7 Fixer 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Kayba Stage 7 Fixer this skillkayba-ai/agentic-context-engine | 2.6k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Darwin Skill Optimizeralchaincyf/darwin-skill | 6.2k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| CodeGraph Agent Evalcolbymchenry/codegraph | 74k | — | ~950 | Automated safety check: Pass | MIT | |
| Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills | 21k | — | ~1.9k | Automated safety check: Pass | MIT | |
| O2 Review Loopopenobserve/openobserve | 22k | — | ~3.7k | Automated safety check: Pass | AGPL-3.0 | |
| Beads Task Memorygastownhall/beads | 28k | — | ~1.2k | Automated safety check: Pass | MIT |
alchaincyf/darwin-skill
Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.
colbymchenry/codegraph
Benchmarks how much CodeGraph helps a coding agent on a real repository, comparing runs with and without it for a chosen local or published version.
KKKKhazix/khazix-skills
Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.
openobserve/openobserve
Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.
gastownhall/beads
Tracks multi-session work with dependencies in the bd issue tracker so the agent can find ready tasks and recover its context after conversation compaction.
slopus/happy
Searches past Claude Code, Codex and Cursor sessions and summarizes what was worked on, tried or decided, using extraction scripts instead of reading raw logs.
kayba-ai/agentic-context-engine
End-to-end agent evaluation and improvement pipeline. An agent skill from kayba-ai/agentic-context-engine.
kayba-ai/agentic-context-engine
Fetch pre-computed insights from the Kayba API and build a structured summary.
kayba-ai/agentic-context-engine
Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces.
kayba-ai/agentic-context-engine
Define metrics from Kayba insights, implement them as Python measurement code, run against traces, and iterate until the metrics are clean and meaningful.
kayba-ai/agentic-context-engine
Organize computed metrics into a tiered evaluation rubric with leading, lagging, and quality indicators.
kayba-ai/agentic-context-engine
Triage each insight into discard/code-fix/prompt-fix and produce a prioritized action plan with specific recommendations.
Works with
Categories
Implement the approved fixes from the action plan and log all changes. Kayba Stage 7 Fixer is an agent skill from kayba-ai/agentic-context-engine. Implement the approved fixes from the action plan and log all changes.
Kayba Stage 7 Fixer fits situations like: the user says run stage 7; implement fixes; apply action plan; invoked by the kayba-pipeline orchestrator.
Run `npx skills add kayba-ai/agentic-context-engine --skill kayba-stage-7-fixer -a claude-code`. Or copy the skill folder (.claude/skills/kayba-pipeline/stage-7-fixer in kayba-ai/agentic-context-engine) into .claude/skills/kayba-stage-7-fixer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add kayba-ai/agentic-context-engine --skill kayba-stage-7-fixer -a codex`. Or copy the skill folder (.claude/skills/kayba-pipeline/stage-7-fixer in kayba-ai/agentic-context-engine) into .agents/skills/kayba-stage-7-fixer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kayba-ai/agentic-context-engine --skill kayba-stage-7-fixer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kayba-stage-7-fixer, .gemini/skills/kayba-stage-7-fixer, .github/skills/kayba-stage-7-fixer and .opencode/skills/kayba-stage-7-fixer in your project.
Going by SKILL.md and its folder, Kayba Stage 7 Fixer needs the command-line tools its instructions call (git and python). Our summary lists: Python 3.
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Kayba Stage 7 Fixer is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.8k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Kayba Stage 7 Fixer: Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars), CodeGraph Agent Eval (colbymchenry/codegraph, 74k stars), Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars) and O2 Review Loop (openobserve/openobserve, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
kayba-ai (a GitHub organization) maintains it in kayba-ai/agentic-context-engine, which has 2,590 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 24, 2026.
Source: kayba-ai/agentic-context-engine on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.