bisect-aware-instrumentation

Instrument code to support efficient git bisect by producing deterministic pass/fail signals and concise runtime summaries for each tested commit. Use when debugging regressions with git bisect, automating bisect workflows, creating bisect test scripts, handling flaky tests during bisection, or needing clear exit codes and logging for automated bisect runs. Helps identify the exact commit that introduced a bug through automated testing.

1.30x

Quality

72%

Does it follow best practices?

Impact

86%

1.30x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bisect-aware-instrumentation/SKILL.md

Quality

Content

61%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 practical, code-heavy guide with executable bash examples and real referenced bundle files. It is held back by repetition across similar scripts, lack of an explicit pre-bisect validation step in the core workflow, and some content that duplicates the provided scripts/references.

Suggestions

Add an explicit validation checkpoint to the core workflow: 'Test the script on known good and bad commits before bisecting' as a numbered step with a fix-retry loop, since this is a destructive/automated batch operation.

De-duplicate the near-identical bash scaffolding across the Instrumentation Patterns and Advanced Techniques by linking to scripts/bisect_template.sh and showing only the differing logic inline.

Fix the template's unbound TEST_RESULT variable (set on the timeout line only inside a failed branch) so the example is correct as written.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable examples, but the body repeats similar bash scaffolding across six near-identical scripts and re-states concepts like the exit-code convention already shown in the template, which could be tightened.	3 / 5
Actionability	Provides concrete, copy-paste-ready bash scripts with real commands (make build, pytest, timeout, git bisect run) covering common cases, with only minor gaps such as undefined TEST_RESULT handling in the template.	4 / 5
Workflow Clarity	The five-step workflow is sequenced, but it is a batch/automated operation with no explicit validation checkpoint verifying the script on known good/bad commits before bisecting (mentioned only as a best-practice bullet), and no fix-retry feedback loop.	3 / 5
Progressive Disclosure	Good structure with a clear overview and four real bundle files (references/git_bisect_guide.md, references/exit_codes.md, scripts/bisect_template.sh, scripts/bisect_wrapper.py) referenced one level deep, though some inlined bash could move to the script bundle.	4 / 5
	Total	14 / 20 Passed

Description

83%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 strong: it pairs a clear statement of what the skill does with an explicit, multi-clause 'Use when...' trigger list and uses third-person voice throughout. Minor improvements would be adding common synonyms/file extensions and slightly sharper boundary phrasing against general test-automation skills.

Suggestions

Add common synonyms and concrete file types (e.g. 'bisect scripts', `.sh`, `git bisect run') to broaden natural trigger coverage.

Sharpen the boundary versus general test automation by foregrounding the bisect-specific exit-code/skip semantics in the opening clause.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'producing deterministic pass/fail signals', 'concise runtime summaries', 'handling flaky tests', 'clear exit codes and logging' — giving good coverage with only minor gaps.	4 / 5
Completeness	Explicitly answers both 'what' (instrument code for deterministic pass/fail signals and summaries) and 'when' ('Use when debugging regressions with git bisect, automating bisect workflows...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural triggers users would say ('debugging regressions with git bisect', 'automating bisect workflows', 'flaky tests during bisection') with good coverage, missing a few common synonyms or the `.sh` extension.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (bisect-specific instrumentation) with distinct triggers and minimal conflict risk, though adjacent debugging/test-automation skills share some surface overlap.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ArabelaTso/Skills-4-SE
Path: skills/bisect-aware-instrumentation/SKILL.md
Commit: 4f38503

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.