agentsclimarketplace

Debug with evidence

Skill himanshi-28/coding-agent-skills/skills/debug-with-evidence

Portable Agent Skills for test-first development, evidence-based debugging, code review, and reviewable Git history.

Install
npx -y skills add himanshi-28/coding-agent-skills --skill debug-with-evidence

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 23 days oldThe repository was created 23 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Explicit-invocation workflow for systematic debugging that reproduces failures, forms falsifiable hypotheses, collects runtime evidence, proves root causes, adds regression tests, and verifies targeted fixes. Use only when the user directly invokes the debug-with-evidence skill.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.6 KB, 449 tokens by cl100k_base, as published. Nobody here has run it

Debug with Evidence

Find and prove the root cause before changing behavior. A disappearing symptom is not sufficient evidence of a correct fix.

Workflow

  1. Define the failure.
    • Record observed behavior, expected behavior, exact inputs, environment, frequency, timeline, and recent relevant changes.
    • Separate reported facts from assumptions.
  2. Establish a reliable reproduction.
    • Reproduce with the smallest safe case available.
    • Preserve the failing command, request, data shape, or user steps.
    • If reproduction is impossible, identify the missing evidence instead of guessing.
  3. Trace the relevant code path.
    • Inspect applicable instructions, entry points, state transitions, dependencies, error handling, and existing tests.
  4. Form ranked hypotheses.
    • Make each hypothesis specific and falsifiable.
    • State the observation that would support or reject it.
  5. Collect targeted evidence.
    • Use existing logs, stack traces, test output, browser state, query plans, profiles, metrics, or version history.
    • Add minimal temporary instrumentation at suspected boundaries when needed.
    • Change one investigative variable at a time.
  6. Identify the root cause.
    • Explain the causal chain from triggering condition to observed failure.
    • Show why the evidence favors it over competing hypotheses.
    • Reject symptom-masking fixes such as an unexplained null check or broad retry.
  7. Lock a regression test.
    • Add the smallest test that reproduces the bug and confirm it fails for the proven reason before applying the fix.
    • Use the lock-tests-first skill when the contract requires broader coverage.
  8. Apply a targeted fix.
    • Correct the cause with the smallest coherent change.
    • Preserve unrelated behavior and remove temporary instrumentation unless it provides lasting observability value.
  9. Verify.
    • Re-run the reproduction and regression test, then relevant surrounding checks.
    • Test boundary and failure cases suggested by the root cause.
    • Explain why the fix prevents recurrence rather than hiding the symptom.

Output

Provide the reproduction, evidence, root cause, rejected hypotheses, fix, regression protection, verification results, and residual uncertainty. Never claim a cause solely because a patch made the immediate error disappear.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 1 of the 12 instructions most debug triage skills give in 449 tokens

Counted across 839 of the 1,149 authors here whose files we hold, read 2026-08-07

  • investigate root cause before proposing any fixin 102 of 839, across 67 files
  • read error messages completelyin 89 of 839, across 49 files
  • create a failing test case before fixingin 84 of 839, across 46 files
  • reproduce the issue consistentlyin 82 of 839, across 41 files
  • change one variable at a timein 82 of 839, across 42 files
  • check recent changesin 74 of 839, across 36 files
  • write the regression test before fixinghere, and in 74 of 839, across 40 files
  • fix the root cause not the symptomin 60 of 839, across 45 files
  • implement a single fix at a timein 59 of 839, across 20 files
  • trace data flow backward to the sourcein 50 of 839, across 20 files
  • remove all debug instrumentationin 49 of 839, across 13 files
  • form a single hypothesisin 48 of 839, across 18 files

Said here and by no other author read

  • collect targeted runtime evidence
  • apply the smallest coherent fix
  • provide all evidence and reasoning

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.