CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

1k-retrospective

Analyze accumulated bug fix cases and propose updates to the self-testing checklist. Use periodically (weekly/monthly) to evolve quality checks based on real issues.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.skillshare/skills/1k-retrospective/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, well-sequenced instruction skill that externalizes its bulk data appropriately and gates risky writes behind user confirmation. Remaining gaps are small: an undefined root-cause taxonomy, no post-change verification step, and a dangling reference to references/patterns.md.

Suggestions

Define or reference a fixed root-cause category list so pattern aggregation stays consistent across runs.

Add a brief post-change verification in Step 5/6, e.g. re-check the 150-line limit after edits and confirm the completion marker was appended.

Create references/patterns.md (or drop the mention) so the overflow destination named in Step 5 actually exists.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: six terse steps, no concept explanations, a compact report template, and a 2-line worked example — every token earns its place, matching the lean-and-efficient anchor.

5 / 5

Actionability

Guidance is highly concrete for an instruction-only skill (exact file paths, 2+/3+ pattern thresholds, a copy-ready report format, and edit rules like the 150-line cap and '[ARCHIVED]' prefix), but 'root cause category' is never given a taxonomy, leaving a minor gap that keeps it below fully-executable.

4 / 5

Workflow Clarity

The six steps are clearly sequenced with real checkpoints — a stop gate at fewer than 3 cases and 'after user confirmation' before modifying rules — but there is no post-change verification (e.g., re-checking the 150-line limit or confirming the marker was appended), which the 5 anchor requires.

4 / 5

Progressive Disclosure

The 243KB case log is correctly externalized to references/case-studies.md (verified to exist) and the body stays a concise overview, but Step 5 points to references/patterns.md which is absent from the bundle — a minor organization gap against the actual bundle structure.

4 / 5

Total

17

/

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.

A solid description that clearly states what the skill does and gives an explicit usage cadence with a distinct niche. It is held back by narrow action coverage and a thin set of natural trigger synonyms.

Suggestions

Add one or two more concrete actions to broaden coverage, e.g. 'generate a pattern report and archive resolved cases'.

Include natural trigger phrases users would actually say, such as 'Use when the user asks for a retrospective, post-mortem, or wants to update self-testing rules from lessons learned'.

Name the key artifacts involved (case-studies log, self-testing.mdc) so the description surfaces them for skill selection.

DimensionReasoningScore

Specificity

Names the domain ('bug fix cases', 'self-testing checklist') and exactly two concrete actions ('Analyze accumulated bug fix cases', 'propose updates'), matching the 1-2-actions anchor; it stays below 4 because broader capabilities (reporting, archiving, gap thresholds) are absent.

3 / 5

Completeness

Both parts are explicit: a clear 'what' ('Analyze accumulated bug fix cases and propose updates to the self-testing checklist') and a 'when' ('Use periodically (weekly/monthly)'), but the when-clause states cadence rather than concrete user trigger phrases, so it does not reach 5.

4 / 5

Trigger Term Quality

Relevant keywords like 'bug fix cases', 'self-testing checklist', 'quality checks', and 'weekly/monthly' are present, but common natural variations users would say — 'retrospective', 'post-mortem', 'lessons learned', 'recurring bugs' — are missing, fitting the some-keywords-but-missing-synonyms anchor.

3 / 5

Distinctiveness Conflict Risk

The niche is distinct — analyzing accumulated bug-fix cases to evolve a self-testing checklist — and the periodic cadence plus domain-specific nouns make it unlikely to fire for unrelated skills, matching the clear-niche anchor.

5 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

referenced_paths_exist

Referenced path issues: 1 possibly missing (references/patterns.md)

Warning

Total

14

/

16

Passed

Repository

OneKeyHQ/app-monorepo

Path

.skillshare/skills/1k-retrospective/SKILL.md

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.