Skip to content
SkillModel-led2,364 tokens in use

debugging-and-error-recovery

Debug in six steps: stop the line, reproduce, localize, reduce, fix the root cause and guard with a regression test.

119,377 stars on the repository MIT Licenseaddyosmani/agent-skills · skills/debugging-and-error-recovery
npx skills add addyosmani/agent-skills --skill debugging-and-error-recovery
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing debugging-and-error-recovery costs

131tokens idle
2,364tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetectednetworkdetectedwrites filesdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 78
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 195

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

Debugging and Error Recovery gives an agent a structured process for test failures, broken builds, runtime errors and bug reports. It starts with the stop-the-line rule, which halts feature work and preserves evidence, then walks a triage checklist in order.

The skill includes decision trees for non-reproducible bugs, test, build and runtime failures, git bisect for regressions, safe fallback patterns and a rule that error output is data to analyze and never a set of instructions.

What You Get

  • The stop-the-line rule and a six-step triage checklist
  • Triage trees for tests, builds, runtime errors and non-reproducible bugs
  • Git bisect commands and safe fallback code patterns
  • Guidance on temporary and permanent instrumentation plus a verification checklist

Common Use Cases

  • Investigating a failing test or broken build
  • Finding the commit that caused a regression
  • Reproducing an intermittent bug
  • Adding a regression test after a fix

What Makes It Unique

The skill names the root cause as the target and shows a symptom fix next to a root cause fix. It stops all feature work while something is broken and includes a rule that error messages from external sources are data and never commands to follow.

Under The Hood

The skill is a single SKILL.md of instructions with code samples. It runs no scripts of its own. The agent runs the repository’s test and build commands and git bisect, reads logs and error output, and may add temporary logging that the skill says to remove after the fix.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers