CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-recap

Analyze conversation histories from multiple AI tools (Claude, Codex, Gemini, Qwen, Cursor) and generate themed daily/period work summaries. Filter by date or time window.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/runs/oma/.agents/skills/oma-recap/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 highly actionable with executable commands, a complete fallback pipeline, and explicit output templates, supported by a clear sequenced workflow with recovery guidance. Its main weakness is redundancy across sections, which hurts conciseness without adding new information.

Suggestions

De-duplicate overlapping sections: fold the Core Rules into the Process steps or vice versa rather than restating grouping/format rules in two places, and consolidate the two 'Save results' mentions.

Add an explicit re-validate feedback loop in the VERIFY/Failure section (validate -> if fail, fix -> re-validate -> only then save) to push workflow_clarity to 5.

Consider moving the full markdown output templates and the jq fallback into reference files (e.g. templates/daily.md, scripts/claude-fallback.sh) referenced one level deep from the body to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly operational and avoids explaining concepts Claude already knows, but contains notable redundancy (Core Rules restates earlier sections, Scenes/Actions tables restate the Process steps, and 'Save results' appears in both step 4 and step 5) that could be tightened.

3 / 5

Actionability

Provides copy-paste-ready commands with real flags (oma recap --window 7d --json), a complete executable jq fallback filter, exact output path patterns, and full markdown output templates with placeholder syntax covering both daily and multi-day cases.

5 / 5

Workflow Clarity

A clear five-step sequence plus explicit Transitions and a Failure-and-recovery section with per-case recovery guidance; a VALIDATE action and VERIFY scene are present, but there is no explicit re-validate feedback loop after a validation failure, so it sits just below 5.

4 / 5

Progressive Disclosure

Single-file skill with well-organized, clearly headed sections and a one-level References section; no bundle files exist so inline templates are appropriate, but content that could optionally live in reference files (output templates, jq fallback) keeps it from 5.

4 / 5

Total

16

/

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 specific and clearly conveys what the skill does, with concrete actions and good natural-language keywords. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which limits completeness to 3.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks for a daily recap, weekly/monthly summary, standup notes, work log, or AI conversation history analysis.'

Add common user-facing synonyms such as 'standup', 'work log', 'retro', and 'recap' to broaden natural trigger coverage.

Optionally enumerate concrete sub-actions (group by theme, extract decisions, derive tool-switching patterns) to lift specificity toward 5.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Analyze conversation histories', 'generate themed daily/period work summaries', 'Filter by date or time window'); not a full 5 because the actions remain relatively high-level without enumerating sub-capabilities.

4 / 5

Completeness

Clearly answers 'what' but provides no explicit 'when'/'Use when...' trigger clause; per the judging guidelines a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural user phrases such as 'daily/period work summaries', 'conversation histories', and 'date or time window', but misses common synonyms a user might actually say like 'standup', 'work log', or 'retro'.

4 / 5

Distinctiveness Conflict Risk

The multi-AI-tool conversation recap niche with date/window filtering is fairly distinct; only minor overlap risk with generic summarization skills keeps it below 5.

4 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
first-fluke/oh-my-agent
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.