propose-skill-update
Use when 3+ distinct occurrences suggest a skill should be updated with a new trigger, anti-pattern, or verification step
Skill by thesyntaxninja
Chalk Labs
Need help deploying propose-skill-update?
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/thesyntaxninja-propose-skill-update
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/propose-skill-update
What's inside
- Skill name
propose-skill-update- Description
- Use when 3+ distinct occurrences suggest a skill should be updated with a new trigger, anti-pattern, or verification step
- License
- MIT
- Instructions
- 86 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Propose Skill Update ## Quick Reference When you observe 3+ distinct occurrences of a pattern, propose a skill update. Only specific additions are allowed. Core process rewrites are never allowed. The user approves before any change. ## When to Use - You've seen the same trigger condition 3+ times that isn't in a skill - You've seen the same anti-pattern 3+ times that isn't documented - A verification step was needed 3+ times that isn't in the checklist - `compound-docs` has captured 3+ learnings about the same topic ## When NOT to Use - Fewer than 3 distinct occurrences (one-offs aren't patterns) - The update would rewrite a skill's core process - The update adds project-specific details to a general skill - You're unsure — wait for more evidence ## The Ratchet: What's Allowed | Allowed | Must Cite 3+ Occurrences | |---------|--------------------------| | New trigger condition | "I've seen this trigger 3 times: [evidence]" | | New anti-pattern | "This mistake has happened 3 times: [evidence]" | | New verification step | "This check was needed 3 times: [evidence]" | | Never Allowed | Reason | |---------------|--------| | Rewriting core process | Core processes are stable — propose a new skill instead | | Removing steps | Removal requires explicit user decision, not automated ratchet | | Adding project-specific details | Skills are general. Use `dojo.config.md` for project specifics. | | Changing skill priority/gate status | Architecture decision, not an automated update | ## Core Process ### Step 1: Gather Evidence Document the 3+ occurrences: ``` SKILL UPDATE PROPOSAL: <skill-name> Type: new trigger | new anti-pattern | new verification step Evidence: 1. [Date/context] — [what happened] 2. [Date/context] — [what happened] 3. [Date/context] — [what happened] Proposed Addition: [The exact text to add to the skill] Location in Skill: [Which section: triggers, Anti-Patterns table, or verification checklist] ``` ### Step 2: Present to User > "I've noticed [pattern] across 3 separate instances. I'd like to add it to the `<skill-name>` skill. Here's the proposal:" > > [Show the proposal] ### Step 3: Apply If Approved If the user approves: 1. Edit the SKILL.md file with the addition 2. Update the frontmatter if a new trigger was added 3. Run `build-index.ts` to regenerate the index 4. Note the update in a learning (`compound-docs`) ## Anti-Patterns | Anti-Pattern | Why It's Wrong | |--------------|----------------| | Proposing updates from 1-2 occurrences | Not enough evidence. Wait for 3. | | Rewriting instead of appending | The ratchet only adds. It never rewrites. | | Adding without user approval | Skills belong to the user. Always ask first. | | Project-specific additions to general skills | Use config, not skill edits. | ## Chaining None — this is a terminal skill.
From thesyntaxninja/syntaxninja-dojo, MIT.
More from thesyntaxninja/syntaxninja-dojo
- 0.443score
receiving-code-review
thesyntaxninja
Use when receiving code review feedback — requires technical verification of each suggestion before implementing, not blind agreement
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
requesting-code-review
thesyntaxninja
Use when implementation is complete and a comprehensive code review is needed — dispatches parallel review agents and merges findings
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
executing-plans
thesyntaxninja
Use when an approved plan exists and implementation should begin — executes steps sequentially with verification checkpoints
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
ralph-loop
thesyntaxninja
Use when task scope exceeds one context window and decomposes into independent pass/fail stories with clean iteration boundaries
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
self-review
thesyntaxninja
Use when implementation is complete and verification has passed — dispatches the sensei agent for fresh-context quality review
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
subagent-driven-development
thesyntaxninja
Use when executing an implementation plan with independent tasks that can be delegated to subagents within the current session
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
verification-before-completion
thesyntaxninja
Use when about to claim work is complete, fixed, or passing — requires running verification commands and confirming output before making any success claims
SkillDFreshness: D★ 2Claude Code +9 - 0.442score
writing-plans
thesyntaxninja
Use when a task requires multiple steps and benefits from a structured plan before implementation begins
SkillDFreshness: D★ 2Claude Code +9 - 0.442score
prd-generator
thesyntaxninja
Use when a structured PRD document is needed for the ralph loop — generates prd.json and progress.txt
SkillDFreshness: D★ 2Claude Code +9 - 0.442score
story-decomposition
thesyntaxninja
Use when a large task needs to be broken into independent, verifiable stories with pass/fail acceptance criteria
SkillDFreshness: D★ 2Claude Code +9 - 0.442score
brainstorming
thesyntaxninja
Use when requirements are unclear, ambiguous, or have multiple valid interpretations — before planning or implementing
SkillDFreshness: D★ 2Claude Code +9 - 0.442score
compound-docs
thesyntaxninja
Use when a hard problem was just solved and the solution should be captured as a learning for future reference
SkillDFreshness: D★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 4, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from thesyntaxninja
- 0.443score
self-review
thesyntaxninja
Use when implementation is complete and verification has passed — dispatches the sensei agent for fresh-context quality review
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
executing-plans
thesyntaxninja
Use when an approved plan exists and implementation should begin — executes steps sequentially with verification checkpoints
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
requesting-code-review
thesyntaxninja
Use when implementation is complete and a comprehensive code review is needed — dispatches parallel review agents and merges findings
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
ralph-loop
thesyntaxninja
Use when task scope exceeds one context window and decomposes into independent pass/fail stories with clean iteration boundaries
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
receiving-code-review
thesyntaxninja
Use when receiving code review feedback — requires technical verification of each suggestion before implementing, not blind agreement
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
subagent-driven-development
thesyntaxninja
Use when executing an implementation plan with independent tasks that can be delegated to subagents within the current session
SkillDFreshness: D★ 2Claude 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 propose-skill-update 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
propose-skill-update. Agent Mart. https://agentmart.dev/skills/thesyntaxninja-propose-skill-update (last updated 2026-10-24)