CtrlK
BlogDocsLog inGet started
Tessl Logo

aw-create-walkthrough

Generate a walkthrough artifact (walkthrough.md) in `.agent/{branch}/` summarizing completed work for PR delivery. Gathers information from plan.md, git history, and test results to produce a comprehensive summary. Use at Phase 6 before creating the draft PR. Triggers on create walkthrough, generate walkthrough, write walkthrough artifact.

69

Quality

87%

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

81%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.

A well-structured, actionable skill body: concrete bash commands for artifact placement and information gathering, a complete template, and an explicit validation checklist with prerequisites. The main weaknesses are mild repetition (branch-name and presentation instructions restated), a vague test-status step, and unsourced template placeholders.

Suggestions

State the branch-name warning once (Step 1's command already guarantees it) and merge the Delivery section's presentation requirement into Step 3 to remove the repetition flagged in conciseness.

Replace "Recall or re-run the test suite to confirm current status" with a concrete command example (e.g., the project's test invocation) or an explicit instruction to run the suite and record the command used.

Add brief sourcing guidance for the {PR_NUMBER} and {WORKTREE_PATH} template placeholders (e.g., `gh pr list --head $BRANCH` and `git worktree list`) so the template is fully copy-paste executable.

DimensionReasoningScore

Conciseness

The body is efficient with concrete commands and no explanations of known concepts, but "do NOT guess the branch name" is repeated in Steps 1 and 2, and the present-to-user instruction appears three times (Step 3, checklist, Delivery section), matching anchor 4's "minor instances that could be trimmed".

4 / 5

Actionability

Provides copy-paste-ready bash commands for gathering git info and a complete walkthrough template, but "Recall or re-run the test suite to confirm current status" is vague and the {PR_NUMBER} and {WORKTREE_PATH} placeholders lack instructions on where to source them — minor gaps consistent with anchor 4 rather than fully executable anchor 5.

4 / 5

Workflow Clarity

Steps 1–3 are clearly sequenced with prerequisites stated up front, and an explicit 9-item Validation Checklist (path, frontmatter, timestamps, summary, changes table vs. git diff --stat, decisions, testing, verification, presentation) closes the loop, matching anchor 5's explicit validation steps and checklists for complex processes.

5 / 5

Progressive Disclosure

No bundle files exist and the body has clear sections (Prerequisites, Procedure, Template, Validation Checklist, Delivery) with easy navigation, but at ~135 lines it exceeds the simple-skill threshold and inlines a ~55-line template that could arguably live in a separate reference file, matching anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A strong description: concrete actions with named sources (plan.md, git history, test results), an explicit use-when clause tied to the delivery workflow phase, and natural trigger phrases. The only weaknesses are modest trigger-synonym coverage and non-exhaustive description of the artifact's contents. Uses third-person voice throughout with no over-claims.

DimensionReasoningScore

Specificity

Names several concrete actions — "Generate a walkthrough artifact (walkthrough.md) in `.agent/{branch}/`" and "Gathers information from plan.md, git history, and test results" — but does not comprehensively cover what the artifact contains, matching anchor 4 rather than 5.

4 / 5

Completeness

Explicitly answers both what ("Generate a walkthrough artifact... summarizing completed work for PR delivery") and when ("Use at Phase 6 before creating the draft PR" plus concrete trigger phrases), matching anchor 5; not 4 because the when-clause is explicit rather than merely present.

5 / 5

Trigger Term Quality

"Triggers on create walkthrough, generate walkthrough, write walkthrough artifact" provides good natural verb-phrase coverage, but misses common synonyms such as "summary", "PR summary", or "changelog", so it falls short of anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

The "walkthrough" artifact niche with distinct trigger phrases ("create walkthrough, generate walkthrough, write walkthrough artifact") and a specific output path (`.agent/{branch}/walkthrough.md`) gives minimal conflict risk, matching anchor 5 rather than the minor-overlap framing of anchor 4.

5 / 5

Total

18

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mthines/agent-skills
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.