CtrlK
BlogDocsLog inGet started
Tessl Logo

gstack-openclaw-retro

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware with per-person contributions, praise, and growth areas. Use when asked for weekly retro, what shipped this week, or engineering retrospective.

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

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.

A highly actionable, well-sequenced retrospective procedure with concrete git commands and output templates. Its main weaknesses are length/redundancy and the absence of any progressive disclosure — everything lives in one long SKILL.md with no reference files.

Suggestions

Move the detailed per-step output templates and narrative section structure into a reference file (e.g. references/output-format.md) and link to it from the body to apply progressive disclosure.

Remove the 'Important Rules' section's restatements of points already covered inline (local timezone, Telegram formatting, commit-anchored praise) to reduce redundancy and token cost.

Collapse the repetitive git-log command blocks in Step 1 into a single parameterized snippet with a small table of the --format variants to tighten the procedure.

DimensionReasoningScore

Conciseness

The body is mostly efficient instruction and commands without explaining concepts Claude already knows, but the ~300-line monolithic procedure and the 'Important Rules' section restate points already made in the steps, so it could be tightened.

2 / 3

Actionability

Provides copy-paste-ready, executable git commands with exact --format strings and concrete output templates (leaderboard, hourly histogram, percentage bars), leaving little ambiguous.

3 / 3

Workflow Clarity

Fourteen clearly sequenced steps with explicit conditional branches ('If solo repo', 'If no prior retros exist', compare mode) and a DONE/DONE_WITH_CONCERNS/BLOCKED completion gate that acts as a checkpoint; the operation is read-only so heavy validation loops are not required.

3 / 3

Progressive Disclosure

Well-organized into labeled sections but entirely monolithic with no bundle files and no one-level-deep references; detailed material such as the narrative structure and per-metric definitions is inline where it could be externalized.

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.

A strong, third-person description that names concrete capabilities, provides natural trigger terms, and explicitly answers both 'what' and 'when'. It is concise without padding and clearly occupies a distinct niche.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Analyzes commit history, work patterns, and code quality metrics', 'per-person contributions, praise, and growth areas' — rather than vague language.

3 / 3

Completeness

Explicitly states what it does (analyze commit history, work patterns, code quality) and when to use it via an explicit 'Use when...' clause, satisfying both halves.

3 / 3

Trigger Term Quality

'Use when asked for weekly retro, what shipped this week, or engineering retrospective' covers natural phrasings a user would actually say, including the colloquial 'what shipped this week'.

3 / 3

Distinctiveness Conflict Risk

The weekly engineering-retrospective niche with git-commit-analysis triggers is distinct and 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
garrytan/gstack
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.