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.

Quality

57%

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 ./benchmarks/runs/oma/.agents/skills/oma-recap/SKILL.md

Quality

Content

56%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 skill body is highly actionable, with concrete commands, an executable fallback, explicit output templates, and a clear five-step process with failure handling. Its main weaknesses are significant redundancy from meta-framework scaffolding sections that restate the Process rules, and a monolithic structure that inlines templates and scripts that belong in separate bundle files. Trimming the scaffolding and splitting the templates would substantially improve token efficiency and organization.

Suggestions

Delete or collapse the 'Scheduling', 'Structural Flow', and 'Logical Operations' scaffolding sections (including the empty 'Guardrails' heading and the 'SSL primitive'/'Resource scope' tables); the numbered Process and Core Rules already cover that content.

Move the daily and multi-day output templates into a references/ file (e.g., references/templates.md) and the jq fallback into scripts/, keeping only usage pointers in SKILL.md.

Make the fallback script portable (the 'date -j -f' invocation is macOS-only) and add an explicit VERIFY step at the end of the Process so validation is a real checkpoint, not just a 'Scenes' label.

Dimension	Reasoning	Score
Conciseness	Roughly 80 lines of the body ('Scheduling', 'Structural Flow', 'Logical Operations') are framework scaffolding that duplicates rules restated in 'Process' and 'Core Rules' (e.g., 'If no date is specified, use today' vs. 'No date specified → today'), plus an empty 'Guardrails' heading and abstract tables ('SSL primitive', 'Resource scope' with LOCAL_FS/PROCESS) that add no actionable value. This is noticeably verbose with several padded sections rather than merely 'some unnecessary explanation' (anchor 3).	2 / 5
Actionability	The guidance is mostly executable: copy-paste commands ('oma recap --json', '--window 7d', '--date YYYY-MM-DD', '--tool claude,gemini'), a complete inline jq fallback script, concrete file paths, and full output templates with examples. Not anchor 5 because the fallback script uses BSD-only 'date -j -f' syntax (fails on Linux) and the theme-analysis step is unavoidably directive rather than executable.	4 / 5
Workflow Clarity	The 5-step Process (Resolve Date → Collect Data → Theme Analysis → Output Format → Save Results) is a clear sequence with explicit grouping thresholds and a 'Failure and recovery' section covering missing history, ambiguous timestamps, and sparse data. Not anchor 5 because VERIFY appears only in the 'Scenes' list, not as an actual validation step in the Process, so checkpoints are implicit rather than explicit.	4 / 5
Progressive Disclosure	Section headers are clear and navigation within the file is reasonable, but the entire skill is one ~300-line monolith with no bundle files: both full output templates and the jq fallback script are inlined where they could live in references/ or scripts/. This matches 'some structure but content that should be separate is inline' rather than anchor 4's 'most content is appropriately placed'.	3 / 5
	Total	13 / 20 Passed

Description

58%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 concrete about what the skill does and which tools it covers, with a well-defined niche. Its main weakness is the missing 'Use when...' trigger clause and the absence of natural trigger phrases like 'recap', 'standup', or 'work log' that users would actually say. Adding an explicit use-when clause with those synonyms would lift both completeness and trigger term quality.

Suggestions

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

Include natural synonyms users would say ('recap', 'summarize my work', 'what did I do today') alongside the current domain terminology.

Mention the concrete output (a Markdown recap file) so the 'what' coverage is complete.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions ('Analyze conversation histories from multiple AI tools (Claude, Codex, Gemini, Qwen, Cursor)', 'generate themed daily/period work summaries', 'Filter by date or time window') with a clearly named domain. It falls short of anchor 5 because coverage has minor gaps, e.g., no mention of the saved Markdown output or the standup/retro use cases.	4 / 5
Completeness	The 'what' is clear (analyze multi-tool conversation histories, generate themed summaries, filter by date/window), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. 'Filter by date or time window' describes an input, not when to invoke the skill.	3 / 5
Trigger Term Quality	Relevant keywords like 'conversation histories', 'work summaries', and 'daily/period' are present, but common natural phrases a user would say ('recap', 'summarize my day', 'standup notes', 'work log') are missing. Not anchor 2 because the terms present are specific to the domain rather than generic.	3 / 5
Distinctiveness Conflict Risk	The description carves out a clear niche (conversation histories from specific named AI tools, themed summaries) with minor overlap risk against generic summarization skills. It is not anchor 5 because 'work summaries' is a fairly broad phrase that could collide with general reporting or retro skills.	4 / 5
	Total	14 / 20 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: benchmarks/runs/oma/.agents/skills/oma-recap/SKILL.md
Commit: ce19702

Reviewed: 4 days 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.