Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Vibe-Marketer/plugins-and-skills --skill heal-skillsgit clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vibe-marketer/plugins-and-skills/heal-skills)<a href="https://agentmods.dev/skills/vibe-marketer/plugins-and-skills/heal-skills"><img src="https://agentmods.dev/badge/skills/vibe-marketer/plugins-and-skills/heal-skills/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vibe-marketer/plugins-and-skills/heal-skills"><img src="https://agentmods.dev/badge/skills/vibe-marketer/plugins-and-skills/heal-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00109 | $0.01401 |
| Opus 5 | $0.00055 | $0.00700 |
| Sonnet 5 | $0.00022 | $0.00280 |
| Haiku 4.5 | $0.00011 | $0.00140 |
Grade A, and why
heal-skills scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
-
Diagnose Before Fixing. Never jump to a fix without understanding the failure. Read the skill thoroughly, reproduce the issue mentally, and identify the specific root cause before proposing changes.
-
Minimal Fixes. Change as little as possible. A targeted edit to one section is better than rewriting the whole skill. Minimal changes are easier to verify and less likely to introduce regressions.
-
Show Before/After. Always show the user exactly what will change. No surprises. Display the old content and the proposed new content side by side.
-
Close the Loop. After fixing, suggest re-testing with evaluate-skills. A fix that hasn't been verified is just another guess.
</essential_principles>
<quick_start>
- Provide the skill path and describe what went wrong
- The skill reads and analyzes the skill's files
- Root cause is identified and categorized
- A specific fix is proposed with before/after comparison
- Fix is applied after your approval
- Re-testing is suggested via evaluate-skills </quick_start>
<step_1> Gather Context
Required inputs:
- Skill path (directory or SKILL.md)
- Failure description: What happened? What was expected?
Read the following:
- SKILL.md (always)
- All files in workflows/ (if router skill)
- All files in references/ (scan for relevance)
- Any templates/ or scripts/ mentioned in the failure
Build a mental model of how the skill is supposed to work. </step_1>
<step_2> Reproduce the Failure
Trace the failure through the skill's logic:
- What query or input triggered the failure?
- Which workflow/section was activated?
- Where in the execution path did things go wrong?
- Was it a complete failure or partial degradation? </step_2>
<step_3> Categorize the Issue
Classify into one of these failure categories:
| Category | Symptoms | Typical Root Cause |
|---|---|---|
| Trigger failure | Skill doesn't activate on relevant queries | Description missing keywords, too narrow scope |
| Routing failure | Wrong workflow selected | Routing table ambiguity, overlapping intents |
| Instruction gap | Output misses key requirements | Missing constraint, example, or quality gate |
| Output quality | Output is correct but poor quality | Vague instructions, missing format specification |
| Missing reference | Skill lacks needed domain knowledge | Reference file missing or incomplete |
| Structural issue | Parsing errors, broken XML, YAML errors | Syntax problems in skill files |
| Regression | Skill used to work, now doesn't | Recent edit broke something, dependency changed |
| </step_3> |
<step_4> Propose Fix
For each category, apply the corresponding heal pattern:
Trigger failure:
- Analyze what keywords or phrases are missing from the description
- Propose expanded description with new trigger keywords
- Verify proposed description won't cause false positives
Routing failure:
- Identify the ambiguous routing entry
- Propose clearer intent differentiation
- Add disambiguation keywords or negative matches
Instruction gap:
- Identify the missing constraint or requirement
- Propose the specific addition (tag, sentence, or section)
- Place it in the correct location (SKILL.md for essential, workflow for procedural)
Output quality:
- Identify what quality dimension is lacking
- Propose format specification, example, or quality gate
- Add to appropriate section (success_criteria, examples, or validation)
Missing reference:
- Identify what domain knowledge is needed
- Propose reference file content or addition to existing reference
- Update reference_index in SKILL.md
Structural issue:
- Identify the syntax error (unclosed tag, invalid YAML, etc.)
- Propose the corrected syntax
- Check for similar issues elsewhere in the skill
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 166 lines · 109 tokens per session scan A 5022ea48317b
heal-skills is a skill published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 109 tokens to every session and 1,401 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.