agent-transcript

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

Quality

83%

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

Quality

Content

100%

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 lean, well-structured, fully actionable skill: concrete commands, a sequenced workflow with validation feedback loops, and clean section organization with a single verified bundle reference. It is strong across all content dimensions.

Dimension	Reasoning	Score
Conciseness	The body is lean: terse Contract bullets and concrete commands with no explanation of concepts Claude already knows; the only minor tightening opportunity is slight redundancy between the Contract trim rules and workflow steps 5-6, but every token largely earns its place.	3 / 3
Actionability	Fully executable bash commands (find, render, preview, append-body, html) with concrete arguments and temp-file paths are given, and the referenced agent-transcript script is verified to exist, making the guidance copy-paste ready.	3 / 3
Workflow Clarity	The 8-step PR/Issue Workflow is clearly sequenced with explicit validation checkpoints: a step-6 inspect-and-trim-again feedback loop, user confirmation in steps 4 and 7, and the Contract's 'fail closed on unresolved secrets' rule.	3 / 3
Progressive Disclosure	Content is organized into clear sections (Contract, Helper, PR/Issue Workflow, Review Artifacts) with a single one-level-deep bundle reference to the agent-transcript script (verified present) and no nested reference chains, giving easy navigation.	3 / 3
	Total	12 / 12 Passed

Description

67%

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 occupies a clear, low-conflict niche, but it lacks explicit 'Use when...' trigger guidance and only covers a narrow slice of the natural terms a user might say. Adding a trigger clause and a few common keyword variations would raise completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when creating or updating GitHub PR/issue bodies for agent-created work and the user wants a redacted transcript attached.'

Broaden natural keyword coverage by including common variations such as 'session logs', 'agent session', 'PR body', 'issue body', and 'redacted log'.

Keep the concrete action list ('redact, preview, and insert') but tie it to the trigger so both 'what' and 'when' are answered in one sentence.

Dimension	Reasoning	Score
Specificity	Names a clear domain ('GitHub PR/issue agent transcripts') and three concrete actions ('redact, preview, and insert'), matching the multiple-specific-actions anchor rather than the score-2 'some actions' anchor.	3 / 3
Completeness	It clearly states what the skill does (redact, preview, insert transcripts) but provides no 'Use when...' clause or equivalent explicit trigger for when to use it; per the judging guidelines a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant terms like 'GitHub PR/issue', 'agent transcripts', 'redact', and 'preview' are present, but common user variations such as 'session logs', 'agent session', 'PR body', or 'redacted log' are missing, so it stops at 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The niche is narrow and specialized (provenance for agent-created PR/issue bodies), with distinct triggers that make it unlikely to fire for an unrelated skill, matching the clear-niche anchor.	3 / 3
	Total	10 / 12 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: bb36883

Reviewed: about 14 hours 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.