CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

skill-debug

Debug a reproducible symptom with a bounded feedback loop and original-scenario verification

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-debug/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-gated, disciplined debugging workflow with unusually strong validation checkpoints and error-recovery feedback loops. Its weaknesses are structural: a large inline activation script with redundant prose re-explanation inflates token cost and makes the file monolithic rather than progressively disclosed.

Suggestions

Move the freeze-activation bash block into a scripts/ file (e.g. scripts/freeze.sh) and invoke it in one line; the ~35 lines of code plus the paragraph re-describing its behavior are the body's largest token cost.

Delete or compress the prose that restates what the preceding script already shows (the Python 3 requirement, symlink/empty-state refusal, exclusive-creation details are all readable from the code).

Replace the <module-directory> placeholder with one concrete resolved example so the activation snippet is copy-paste ready as-is.

DimensionReasoningScore

Conciseness

The body is mostly dense, non-obvious instruction (3-Strike Rule, WTF scoring formula, freeze semantics), but the paragraphs following the freeze script re-explain what the just-shown code does ("Activation uses the shared host session resolver and requires a stable session ID", "Both activation and freeze enforcement require Python 3", "Existing empty, symlinked or nonregular state is refused"). That is more than minor over-explanation, so anchor 3 fits better than 4.

3 / 5

Actionability

Guidance is mostly executable: a concrete loop (reproduce, retain failure signature, minimize, test one named hypothesis, verify both scenarios), quantitative rules (+15% per revert, +20% unrelated files, 20% stop threshold), a formatted example output line, and a copy-paste bash block with only a <module-directory> placeholder. Not anchor 5 because the core investigation steps are prose-directed rather than turnkey commands, and the referenced skills/blocks/*.md dependencies live outside this bundle.

4 / 5

Workflow Clarity

Clear sequence with explicit validation checkpoints: the HARD-GATE blocks behavior changes before reproduction and a named hypothesis is tested, both the minimal reproduction and the original scenario must be verified after the fix, and "Confidence is not verification" forces re-running evidence. Feedback loops for error recovery are explicit (3-Strike Rule, mandatory strategy rotation after two failures, inconclusive exit path for missing dependencies). Matches anchor 5.

5 / 5

Progressive Disclosure

The skill is a single ~115-line file with a ~35-line inline bash block plus explanatory prose that clearly belongs in a scripts/ or references/ file; no bundle files exist to offload it. External references are clearly signaled ("Read and apply skills/blocks/debug-feedback-loop.md"), which keeps it above anchor 2, but the structure is monolithic rather than well split — anchor 3.

3 / 5

Total

15

/

20

Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinct, describing a disciplined debugging methodology rather than vague help, but it functions as a "what" only. It reads more like an internal process spec than a user-facing trigger description; folding the trigger field's natural terms into it would materially improve trigger quality and completeness.

Suggestions

Append trigger guidance to the description itself, e.g. "Use when a bug, failing test, or performance regression reproduces; not for non-reproducible issues or already-understood changes" — this would lift completeness from 3 toward 5 and satisfy the 'Use when' guideline.

Include the natural user vocabulary ("bugs", "failing tests", "unexpected behavior", "performance regressions") that currently lives only in the trigger field, so keyword matching works from the description alone.

Name 1-2 more concrete actions (e.g. "reproduce, minimize, and verify fixes") to move specificity from one qualified action toward multi-action coverage.

DimensionReasoningScore

Specificity

"Debug a reproducible symptom with a bounded feedback loop and original-scenario verification" names the domain and attaches specific process constraints, but lists only one action rather than several concrete actions. Not generic enough for anchor 2, and lacks the multi-action coverage of anchor 4.

3 / 5

Completeness

The "what" is clear (debug via bounded feedback loop and original-scenario verification), but the description field contains no "Use when..." clause or equivalent; per the guideline this caps completeness at 3. The frontmatter's separate trigger field mitigates this in practice, but the evaluated text itself only weakly implies "when" via "reproducible symptom".

3 / 5

Trigger Term Quality

"Debug" and "reproducible symptom" are relevant keywords, but the natural phrases users actually say — "bug", "failing test", "error", "crash", "regression" — are absent from the description field (they only appear in the separate trigger field). Fits anchor 3: some relevant keywords, missing common variations.

3 / 5

Distinctiveness Conflict Risk

"reproducible symptom" and "original-scenario verification" carve a mostly distinct niche that excludes non-reproducible or already-understood issues, with only minor overlap risk against closely related debugging skills. "Debug" alone is broad, so anchor 5's minimal-conflict bar is not met.

4 / 5

Total

13

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

nyldn/claude-octopus

Path

.claude/skills/skill-debug/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.