skill-improve
Fixes a skill that gets something wrong, proven on the failing case and on everything it did right before.
Skill by thenavidm
Chalk Labs
Need help deploying skill-improve?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/thenavidm-skill-improve
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/skill-improve
What's inside
- Skill name
skill-improve- Description
- Fixes a skill that gets something wrong, proven on the failing case and on everything it did right before. Not for tidying (skill-tidy) or new skills (skill-create).
- License
- MIT
- Instructions
- 28 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Improve a skill One standard: prove it. An edit that only looks right, with the hope that it works next time, hasn't fixed anything. To clean up a skill that works, use `skill-tidy`. The engine runs as `npx -y @thenavidm/skill-builder@latest`. Where `skill-builder` is installed (`npm install -g @thenavidm/skill-builder`), run `skill-builder` instead: it's the same engine, without the download. ## First, save the current version Copy the whole skill folder to `.agents/skill/history/<name>/<date-and-time>/` and confirm the copy matches. It is the baseline the new version is measured against, and the way back if the change makes things worse. If the skill came from someone else's plugin, ask before changing it: edit a copy under a name of theirs, or suggest the fix to the plugin's author. ## Fix it 1. **The exact failure.** Ask for the real input and the output that was wrong, or their review notes (`feedback.json` from an eval run). "It's off" isn't enough to fix; "it wrote the date as November 10" is. 2. **The cause.** Read the whole skill and find the instruction that produced it, the rule that's missing, or the description that let another skill fire. Say it in one sentence, pointing at the line. A guess isn't a cause. 3. **The smallest change** that removes the cause, written by the `skill-writer` agent from your one-sentence cause, or by you in a tool without agents. A skill that grows a new rule for every case becomes a list nobody can follow. Prefer explaining the reason behind an existing rule over adding a new one. 4. **Prove it.** Add the failing case to `evals/evals.json` as a task with an assertion that failed before. Run `eval` on the new version and on the saved one: ```bash npx -y @thenavidm/skill-builder@latest eval <skill> --runs 3 ``` The failing task must now pass, and every task that passed before must still pass. Where assertions can't capture the difference, give the old and new outputs to the `skill-comparator` agent unlabelled; then have the `skill-reviewer` agent check the changed skill. If the cause was triggering, use `skill-description` instead and prove it with `trigger`. ## Either way Two attempts. If the second still fails its proof, put the saved version back (copy the whole folder, confirm it matches) and say plainly what's left: the fix may need a rebuild with `skill-create`. Report what changed, the before and after numbers, and where the old version is kept.
From thenavidm/skill-builder, MIT.
More from thenavidm/skill-builder
- 0.570score
skill
thenavidm
The entry point to Skill Builder, what it can do, which skill fits a request, setup and a health check.
SkillAFreshness: AClaude Code +9 - 0.567score
skill-create
thenavidm
Builds a new skill that does a task the user's way, from a goal, this chat or a brief, and proves it fires and helps before installing.
SkillAFreshness: AClaude Code +9 - 0.567score
skill-eval
thenavidm
Runs a skill's tasks with and without it in a real AI tool, grades every output and opens a review page.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-repo
thenavidm
Sets up a plugin repository with its README as the spec, licence, changelog, CI, topics and one product.json for every tool's manifest.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-description
thenavidm
Checks that a skill's description fires on the right prompts and not on near misses, in each tool, and rewrites it until it does.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-tokens
thenavidm
Measures what skills and plugins cost in context on every message, against each tool's budget.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-check
thenavidm
Checks a skill or plugin against every AI tool's rules, in code, and explains each fix.
SkillAFreshness: AClaude Code +9 - 0.561score
skill-compete
thenavidm
Builds a better version of someone else's skill or plugin from scratch and proves it on the same tasks, with nothing copied.
SkillAFreshness: AClaude Code +9 - 0.561score
skill-publish
thenavidm
Puts a plugin repository on GitHub, private first, with a description and topics people search for.
SkillAFreshness: AClaude Code +9 - 0.561score
skill-release
thenavidm
Releases a new version that reaches every user, moving version, changelog and manifests together, then tag, GitHub and npm, each after a yes.
SkillAFreshness: AClaude Code +9 - 0.561score
skill-bench
thenavidm
Runs a skill's evals in every installed AI tool, side by side.
SkillAFreshness: AClaude Code +9 - 0.561score
skill-facts
thenavidm
Gives every claim in a skill a source and a checked date, and removes advice nobody can source.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Oct 19, 2026 (13 days ago)
- Last release
- Oct 19, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/thenavidm/skill-builder
- Website
- navid.me
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from thenavidm
- 0.570score
skill
thenavidm
The entry point to Skill Builder, what it can do, which skill fits a request, setup and a health check.
SkillAFreshness: AClaude Code +9 - 0.567score
skill-eval
thenavidm
Runs a skill's tasks with and without it in a real AI tool, grades every output and opens a review page.
SkillAFreshness: AClaude Code +9 - 0.567score
skill-create
thenavidm
Builds a new skill that does a task the user's way, from a goal, this chat or a brief, and proves it fires and helps before installing.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-repo
thenavidm
Sets up a plugin repository with its README as the spec, licence, changelog, CI, topics and one product.json for every tool's manifest.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-check
thenavidm
Checks a skill or plugin against every AI tool's rules, in code, and explains each fix.
SkillAFreshness: AClaude Code +9 - 0.565score
skill-tokens
thenavidm
Measures what skills and plugins cost in context on every message, against each tool's budget.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get skill-improve running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
skill-improve. Agent Mart. https://agentmart.dev/skills/thenavidm-skill-improve (last updated 2026-10-24)