agent-transcript

Requested GitHub PR/issue agent transcripts: redact, trim, preview, and insert safely.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/agent-transcript/SKILL.md

Quality

Content

92%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 an exemplary instruction-only skill: extremely lean, safety-forward with explicit authorization gates and omission paths, and grounded in a real, executable helper script with concrete flags and defaults. The only notable gap is that the preview/insert side of the workflow relies on named modes and prose rather than shown commands, which slightly tempers actionability.

Dimension	Reasoning	Score
Conciseness	The body is lean and dense with unique operational facts — real commands with flags and defaults, path variants, keep/drop lists, and marker rules — with zero explanation of concepts Claude already knows. The authorization rule is stated more than once, but each restatement governs a different phase (preview vs. insert), so every token earns its place.	5 / 5
Actionability	The find and render commands are copy-paste ready with concrete flags (--query, --since-days 14, --max-files) and a verified script path. It falls short of anchor 5 because the preview/html/append-body modes are named but no example invocations are shown, and the critical trim step is prose guidance rather than an executable command or helper.	4 / 5
Workflow Clarity	The flow find → render → trim → inspect → preview → insert is clearly sequenced across two well-ordered sections, with an explicit validation checkpoint ('Inspect the trimmed result; helper redaction is not sufficient disclosure review') and defined failure paths ('Unresolved sensitive content means omit the transcript'; 'No safe match means continue the PR work without transcript'). The warning that preview/append-body re-render the session prevents a real error, so despite involving insertion into a published PR body, validation is not missing and the cap does not apply.	5 / 5
Progressive Disclosure	The skill is a single ~53-line body with clear sections and one bundle script whose path is referenced and exists on disk (scripts/agent-transcript). No reference files are needed for content of this size, and the helper's remaining CLI detail is appropriately left to the script itself.	5 / 5
	Total	19 / 20 Passed

Description

66%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 concise and concrete, clearly stating what the skill does with four specific action verbs in a distinct niche. Its main weakness is the complete absence of 'when to use it' trigger guidance, which both caps completeness and slightly weakens trigger-term coverage since users' natural phrasings for requesting a transcript are never modeled.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user explicitly asks to include, preview, or attach an agent transcript in a PR or issue.'

Include natural synonyms users might say, such as 'session logs', 'chat history', or 'conversation transcript', to broaden trigger matching.

Mention the local-log discovery capability (find across Codex/Claude/Pi/OpenClaw logs) so the description's coverage of the workflow is comprehensive.

Dimension	Reasoning	Score
Specificity	The description names a concrete domain ('GitHub PR/issue agent transcripts') and four specific actions ('redact, trim, preview, and insert safely'). It stops short of anchor 5 because the discovery/find step and the scope-limiting behavior are not mentioned, leaving minor gaps in coverage.	4 / 5
Completeness	The 'what' is clearly stated (redact, trim, preview, insert agent transcripts for GitHub PRs/issues), but there is no 'Use when...' clause or equivalent explicit trigger guidance — only the weakly implied 'Requested'. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Natural trigger terms are present — 'transcripts', 'PR/issue', 'preview' — matching what a user would say when requesting this. It falls short of anchor 5 because common synonyms and variations such as 'session logs', 'chat history', or 'conversation logs' are absent.	4 / 5
Distinctiveness Conflict Risk	'agent transcripts' is a clear niche with distinct triggers and minimal conflict risk. It is not anchor 5 because the broad 'GitHub PR/issue' framing creates minor overlap with general PR-editing and review skills.	4 / 5
	Total	15 / 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: steipete/agent-scripts
Path: skills/agent-transcript/SKILL.md
Commit: 3f8c6a3

Reviewed: 2 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.