oma-recap

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

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/oma-recap/SKILL.md

Quality

Content

77%

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, complete output templates, and a clearly sequenced workflow including validation and recovery. It is weakened by redundant template sections that inflate token cost and by a monolithic, all-inline structure that does not progressively disclose detail into separate files.

Suggestions

Collapse the redundant 'Scheduling' template into the Structural Flow/Process sections and drop the SSL-primitive and Resource-scope tables unless they guide real decisions.

Extract the large daily and multi-day output-format templates into reference files (e.g. references/daily-template.md) referenced one level deep from the body.

Note that the jq fallback uses macOS-only 'date -j -f'; either add a portable Linux variant or justify the platform assumption so the snippet is executable everywhere.

Dimension	Reasoning	Score
Conciseness	Mostly efficient procedural guidance with no basic-concept padding, but the 'Scheduling' template (Goal/Intent signature/When-to-use/Dependencies/Control-flow features) overlaps heavily with the later Structural Flow and Process sections, and the SSL-primitive and Resource-scope tables add framework overhead that could be tightened.	2 / 3
Actionability	Provides copy-paste-ready commands (oma recap --json, --window, --date, --tool), a complete jq fallback pipeline, exact output paths, and fully specified daily/multi-day Markdown templates with concrete thresholds (15+ min, <30 prompts).	3 / 3
Workflow Clarity	Clear sequence (Entry -> PREPARE/ACQUIRE/REASON/ACT/VERIFY/FINALIZE -> numbered Process steps) with an explicit VERIFY checkpoint checking TL;DR, grouping, language, and output path, plus a 'Failure and recovery' section giving feedback loops for missing history, ambiguous timestamps, and sparse data.	3 / 3
Progressive Disclosure	No bundle files exist and all content is inline in a ~300-line single file; sections are well-organized but the large output-format templates are inline monolithic blocks that could be split into references, so structure is only partially disclosed.	2 / 3
	Total	10 / 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 niche, naming concrete actions and supported tools. Its main weakness is the absence of an explicit 'Use when...' trigger clause and missing common trigger phrasings users would naturally say.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a daily recap, weekly/monthly summary, standup notes, or work log from AI tool conversations.'

Include natural trigger terms like 'recap', 'standup notes', 'work log', and 'weekly summary' that users would actually say.

Briefly distinguish from sibling skills (e.g. 'For git-based code retros, use oma retro') to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Analyze conversation histories', 'generate themed daily/period work summaries', 'Filter by date or time window') and even enumerates the supported tools, matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	It clearly answers 'what' but lacks any explicit 'Use when...' trigger clause, so per the judging guidelines completeness is capped at 2 even though the 'when' is weakly implied by 'daily/period' and 'Filter by date'.	2 / 3
Trigger Term Quality	It includes some natural terms ('conversation histories', 'work summaries', 'filter by date') but omits common variations a user would actually say, such as 'recap', 'standup', 'work log', or 'weekly summary', so coverage is incomplete.	2 / 3
Distinctiveness Conflict Risk	The niche is distinct — themed work summaries synthesized from multi-AI-tool conversation histories — and the named-tool list plus output type make it unlikely to trigger for unrelated skills.	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: first-fluke/oh-my-agent
Path: .agents/skills/oma-recap/SKILL.md
Commit: 3021301

Reviewed: about 24 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.