CtrlK
BlogDocsLog inGet started
Tessl Logo

forensics

Post-mortem a failed GSD auto-mode run. Traces from symptom to root cause using `.gsd/activity/*.jsonl`, `.gsd/journal/YYYY-MM-DD.jsonl`, `.gsd/metrics.json`, and `.gsd/auto.lock`. Produces a filing-ready bug report with file:line references and a concrete fix suggestion. Use when asked to "forensics", "post-mortem", "why did auto-mode fail", "trace the stuck loop", "debug the crash", after `/gsd forensics` is invoked, or when a session ended in an unexpected terminal state. Reads existing artifacts — does NOT re-run anything.

72

Quality

88%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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-sequenced, actionable forensics workflow with concrete commands and a ready report template. Its main weakness is mild verbosity in the framing sections and a monolithic structure that could split reference detail into a bundled file.

Suggestions

Tighten the objective/core_principle sections: the read-only constraint is stated three times (core_principle, anti_patterns, success_criteria) — consolidate to one authoritative statement to reduce token overhead.

Move the artifact-format reference (activity JSONL fields, journal event catalog in the context section) into a references/ file and point to it, improving progressive_disclosure and keeping SKILL.md as an overview.

Keep the concrete report template but consider trimming motivational phrasing ('Forensics is archaeology, not re-run') in favor of the already-actionable anti_patterns list.

DimensionReasoningScore

Conciseness

Most detail is necessary domain knowledge (GSD artifact formats, journal event names), but the objective and core_principle sections repeat the read-only emphasis with motivational framing ('Forensics is archaeology, not re-run') that overlaps the anti_patterns list and could be tightened.

2 / 3

Actionability

Provides concrete inspection commands (ps, top -b, cat /proc/*), specific JSONL fields and journal events to search for, and a copy-paste-ready report template with real example paths like `.gsd/activity/042-slice-S02.jsonl:128`.

3 / 3

Workflow Clarity

A clear six-step sequence (locate → reconstruct → cross-reference → name cause → propose fix → report) with explicit cross-reference checkpoints and a success_criteria checklist that functions as a validation gate.

3 / 3

Progressive Disclosure

Sections are well-organized (objective, context, process, anti_patterns, success_criteria) but the content is monolithic in a single file — the detailed artifact-format and journal-event reference tables could live in a separate reference file rather than inline.

2 / 3

Total

10

/

12

Passed

Description

100%

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, trigger-rich, and clearly distinguishes the skill's niche while answering both what it does and when to use it. It also cleanly signals its read-only, non-re-running constraint.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Post-mortem a failed GSD auto-mode run', 'Traces from symptom to root cause', 'Produces a filing-ready bug report with file:line references and a concrete fix suggestion' — rather than vague language.

3 / 3

Completeness

Explicitly answers both what (post-mortem, trace, produce bug report) and when via an explicit 'Use when...' clause enumerating concrete triggers and terminal-state conditions.

3 / 3

Trigger Term Quality

Covers natural phrases users would say — 'forensics', 'post-mortem', 'why did auto-mode fail', 'trace the stuck loop', 'debug the crash' — plus the `/gsd forensics` command invocation.

3 / 3

Distinctiveness Conflict Risk

Scoped to GSD auto-mode failures with GSD-specific artifact paths and triggers, giving it a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
gsd-build/gsd-2
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.