#380 by GitHub stars
thananon/9arm-skills
Four-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb. Recite the mantra block verbatim at the start of any debugging session, then apply the four steps in order before proposing any fix. Trigger on /debug-mantra and proactively w
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/engineering/debug-mantra/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a1fc303b274e
No earlier version was observed for comparison.
skills/engineering/post-mortem/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a1fc303b274e
No earlier version was observed for comparison.
skills/engineering/qwen-agent/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a1fc303b274e
No earlier version was observed for comparison.
skills/engineering/scrutinize/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a1fc303b274e
No earlier version was observed for comparison.
skills/productivity/management-talk/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a1fc303b274e
No earlier version was observed for comparison.
skills/productivity/qwenchance/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a1fc303b274e
No earlier version was observed for comparison.
Verified commit a1fc303b274ed06c32d405ba5a6db00ded6e5663
git clone --filter=blob:none --no-checkout https://github.com/thananon/9arm-skills.git .hotskills/thananon-9arm-skills && git -C .hotskills/thananon-9arm-skills checkout --detach a1fc303b274ed06c32d405ba5a6db00ded6e5663
# Copy each selected skill directory from .hotskills/thananon-9arm-skills into .claude/skills/<skill-name>/Heat
4.5- Star growth, last 7 daysAhead of 70% of tracked repositories
- Star growth, last 24 hoursAhead of 68% of tracked repositories
- Rank movement, last 7 daysAhead of 30% of tracked repositories
- Commits, last 30 daysAhead of 0% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- debug-mantra
skills/engineering/debug-mantra - post-mortem
skills/engineering/post-mortem - qwen-agent
skills/engineering/qwen-agent - scrutinize
skills/engineering/scrutinize - management-talk
skills/productivity/management-talk - qwenchance
skills/productivity/qwenchance
How it works
debug-mantra
When your agent uses it
Four-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb. Recite the mantra block verbatim at the start of any debugging session, then apply the four steps in order before proposing any fix. Trigger on /debug-mantra and proactively whenever debugging starts — user reports a bug, says something is broken/throwing/failing, asks to debug/diagnose/investigate an issue, or pastes a stack trace or error log.
What it loads into context
Frontmatter
107 tokensAlways available to the agent
SKILL.md
1,104 tokensWhen the skill is activated
Reference documents
9,867 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Recite this — verbatim, as the first thing in your first response
- 1. Reproduce reliably
- 2. Know the fail path
- 3. Falsify the hypothesis
- 4. Every run is a breadcrumb
- Operating rules
Files
../../../.claude-plugin/plugin.jsonasset290 bytesSKILL.mdcore4,752 bytesSKILL.mdcore4,752 bytes../post-mortem/SKILL.mddoc13,470 bytes../qwen-agent/SKILL.mddoc5,958 bytes../scrutinize/SKILL.mddoc4,692 bytes../../productivity/management-talk/SKILL.mddoc12,948 bytes../../productivity/qwenchance/SKILL.mddoc4,484 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpost-mortem
When your agent uses it
Write the canonical engineering record of a fixed bug — root cause, mechanism, fix, validation, and how it slipped through. Engineer-audience, code identifiers welcome. Use after a debug session lands a fix, before closing the ticket. Trigger on /post-mortem, when the user says "write the post-mortem / postmortem / RCA / root cause analysis", "document this fix", "write up the root cause", "close out this bug with a writeup", or hands you a fixed-and-validated bug and asks for the writeup.
What it loads into context
Frontmatter
124 tokensAlways available to the agent
SKILL.md
3,157 tokensWhen the skill is activated
Reference documents
3,138 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to invoke
- When NOT to use
- Required inputs — refuse to draft without these
- Structure
- Tone
- Output flow
- Worked example — Tada hang in dumbModel (JIRA-12345)
- Rules
Files
SKILL.mdcore13,470 bytesSKILL.mdcore13,470 bytesSKILL.mdcore13,470 bytes../../productivity/management-talk/SKILL.mddoc12,948 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubqwen-agent
When your agent uses it
Delegate menial, well-scoped coding tasks to a cheap Qwen-backed subagent via the `claude-9arm` command instead of burning Claude tokens/quota. Use when the work is mechanical and low-risk — bulk renames, formatting, boilerplate, find-replace, grep-style search & summarization, reading/condensing logs or files, test/docstring/comment scaffolding, or running builds/linters/tests and reporting pass-fail. Also use when the user says "use qwen", "delegate this", "send it to 9arm/qwen", or "do this cheaply". Do NOT use for architecture, design, debugging judgment, security-sensitive edits, or anything needing this conversation's context.
What it loads into context
Frontmatter
155 tokensAlways available to the agent
SKILL.md
1,402 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The command
- Writing the task prompt (most important step)
- Mind the context window (128k)
- Working directory
- Return contract
- Workflow checklist
- One-time setup (optional, removes repeated prompts)
- When NOT to delegate
Files
SKILL.mdcore5,958 bytesSKILL.mdcore5,958 bytesSKILL.mdcore5,958 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubscrutinize
When your agent uses it
Outsider-perspective end-to-end review of a plan, PR, or code change. First questions intent and whether a simpler/more elegant approach would achieve the same goal, then traces the actual code path (not just the diff) to verify the change does what it claims. Output is concise, actionable, and every call carries its rationale. Trigger on /scrutinize and proactively whenever the user asks to review, audit, sanity-check, or get a second opinion on a plan, PR, diff, design doc, or proposed code change.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
1,087 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Operating stance
- Workflow
- Operating rules
Files
SKILL.mdcore4,692 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmanagement-talk
When your agent uses it
Rewrite engineer-to-engineer content for engineering-org leadership (VPs, directors, PMs, release managers, execs in an engineering-savvy company) and shape it for the channel it is going to — JIRA comment, Slack post, async standup line, email, or meeting talking-points. Trigger when the user asks to write/rewrite for management / exec / VP / director / PM / release manager, asks for an "executive summary / leadership update / status update", says "make this less technical / less jargony", or asks for a slack / email / standup / meeting version of work originally written engineer-to-engineer.
What it loads into context
Frontmatter
140 tokensAlways available to the agent
SKILL.md
3,138 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to invoke
- Audience — what "engineering-org leadership" means
- Tone
- Channel shapes
- Source material
- Output flow
- Worked example — same bug, three channels
- Rules
Files
SKILL.mdcore12,948 bytesSKILL.mdcore12,948 bytesSKILL.mdcore12,948 bytesSKILL.mdcore12,948 bytesSKILL.mdcore12,948 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubqwenchance
When your agent uses it
Keeps a long Claude Code task on-track — breaks out of looping/circular thinking, watches the context budget, bounds internal reasoning, and triggers a clean handoff before the window fills. Use when the model is repeating steps, re-reading the same files, second-guessing in circles, stuck or spinning, or running a long multi-step task at risk of exhausting context. Also use when the user says it is "looping", "going in circles", "stuck", "repeating itself", or asks for a handoff before running out of context.
What it loads into context
Frontmatter
121 tokensAlways available to the agent
SKILL.md
1,083 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Before each step — run this
- 1. Loops — detect and break
- 2. Thinking — keep it bounded
- 3. Context budget — count signals, don't estimate
- 4. Hand off cleanly
Files
SKILL.mdcore4,484 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- debug-mantra
- post-mortem
- qwen-agent
- scrutinize
- management-talk
- qwenchance
Repository facts
- License
- No license detected
- Created
- May 20, 2026
- Last pushed
- Jun 14, 2026
- Forks
- 423
- Open issues
- 0
- Project activity
- Slowing
Rank over the last 12 weeks
Now #380 · best #270 · down 63 in 30 days
- #370 from Oct 31 to Nov 1
- #371 on Nov 2
- #373 on Nov 3
- #374 on Nov 4
- #377 on Nov 5
- #380 since Nov 6
64 earlier periods
- #262 on Aug 2
- #266 on Aug 7
- #269 on Aug 8
- #266 on Aug 9
- #274 on Aug 10
- #270 on Aug 11
- #271 on Aug 12
- #275 on Aug 13
- #272 on Aug 14
- #270 on Aug 15
- #276 on Aug 16
- #274 on Aug 17
- #282 from Aug 18 to Aug 19
- #282 on Aug 21
- #276 on Aug 22
- #283 on Aug 23
- #285 on Aug 24
- #286 from Aug 25 to Aug 26
- #284 on Aug 27
- #286 on Aug 28
- #285 on Aug 29
- #280 on Aug 30
- #287 on Aug 31
- #289 on Sep 1
- #288 on Sep 2
- #296 on Sep 3
- #289 on Sep 4
- #287 on Sep 5
- #290 on Sep 6
- #299 on Sep 7
- #298 from Sep 8 to Sep 10
- #297 on Sep 11
- #303 on Sep 12
- #302 on Sep 13
- #304 on Sep 15
- #302 on Sep 16
- #300 on Sep 17
- #307 on Sep 20
- #307 on Sep 25
- #304 on Sep 26
- #308 on Sep 27
- #315 on Sep 29
- #312 on Sep 30
- #310 on Oct 1
- #314 on Oct 2
- #310 on Oct 3
- #313 on Oct 5
- #317 on Oct 7
- #322 on Oct 8
- #327 on Oct 9
- #321 on Oct 10
- #323 on Oct 11
- #332 on Oct 12
- #333 on Oct 14
- #330 on Oct 15
- #335 on Oct 16
- #339 on Oct 18
- #342 from Oct 19 to Oct 20
- #344 on Oct 21
- #345 from Oct 22 to Oct 23
- #354 on Oct 25
- #366 on Oct 28
- #367 on Oct 29
- #369 on Oct 30
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 2, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 9 notes
skills/engineering/debug-mantra/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/post-mortem/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/post-mortem/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/qwen-agent/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/engineering/qwen-agent/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/productivity/management-talk/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/productivity/management-talk/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/productivity/management-talk/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/productivity/management-talk/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 1 network referencein 1 file: debug-mantra/SKILL.md:26
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show the signal with its line
skills/engineering/debug-mantra/SKILL.md
- Network accessline 26
- **Reliable repro** → capture the exact steps, inputs, and environment as a runnable artifact: failing test, curl script, CLI invocation, replay harness.
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 1 fact
- Network access in prose of the SKILL.mddebug-mantra/SKILL.md:26Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/plugin.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/engineering/debug-mantra/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/engineering/debug-mantra/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/engineering/debug-mantra/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/engineering/debug-mantra/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/engineering/debug-mantra/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/thananon-9arm-skills/)