CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

oma-recap

Summarize AI conversation histories for a specified date or period. Use for daily work recaps and cross-tool activity summaries.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

The canonical home for this skill is oma-recap in first-fluke/oh-my-agent

SKILL.md
Quality
Evals
Security

Quality

Content

73%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 highly actionable, well-sequenced workflow with strong error-recovery and exit criteria, written efficiently apart from some duplication between overview and process sections. Its one significant defect is the dangling reference to resources/output-formats.md, which leaves the core output templates unavailable in the bundle.

Suggestions

Ship resources/output-formats.md with the skill (or inline the daily and multi-day templates into SKILL.md) so the referenced output formats actually exist.

Deduplicate the window-length and CLI-command guidance that currently appears in both the Transitions/Canonical-path overview and the Process subsections, stating each rule once and cross-referencing it.

Merge the "Dependencies" and "References" sections, which list the same resources twice.

DimensionReasoningScore

Conciseness

The body is dense and never explains concepts Claude already knows, but content is noticeably duplicated: window rules appear in both "Transitions" ("If window is 3 days or longer...") and "### 4. Output Format", CLI commands in both the "Canonical command path" and "### 2. Collect Data", and "Dependencies" repeats the "References" section. This matches "mostly efficient but includes some... could be tightened" rather than the minor-trim level of 4.

3 / 5

Actionability

Guidance is fully executable and copy-paste ready: `oma recap --date YYYY-MM-DD --json` variants, a complete jq fallback script with both BSD and GNU date handling and a DST warning, concrete save paths (`.agents/results/recap/{date}.md`), and a supported tool-filter list. It covers the common cases, fitting the top anchor rather than the minor-gaps level of 4.

5 / 5

Workflow Clarity

A clear 5-step canonical path with named cross-references to detailed subsections, an explicit "Failure and recovery" section (missing history, ambiguous timestamps, sparse data), a template check in step 4, and defined Exit criteria for success and partial success. This matches "clear sequence with explicit validation steps; feedback loops for error recovery"; the operation is read-only plus one file write, so the destructive-operation cap does not apply.

5 / 5

Progressive Disclosure

The body delegates its core output formats to `resources/output-formats.md` (referenced in "### 4. Output Format" and again in "References"), but the bundle contains no files at all, so the reference is broken and navigation dead-ends. Scored against the actual bundle structure per the guidelines, this sits at the broken/buried-reference level of 2 rather than 3, since the one reference that exists in text leads nowhere.

2 / 5

Total

15

/

20

Passed

Description

70%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 concise, well-formed description with a clear what and an explicit Use-for trigger clause anchored to a distinct niche. Its main limits are narrow trigger coverage (daily only, missing weekly/standup/work-log variants) and thin capability enumeration.

Suggestions

Broaden the trigger clause to include the variations the skill actually supports, e.g. "Use for daily or weekly recaps, standup notes, and work logs from AI conversation histories".

Add one or two more concrete actions to the what clause, such as grouping activity by project/theme and saving a Markdown recap.

DimensionReasoningScore

Specificity

"Summarize AI conversation histories for a specified date or period" names the domain plus one concrete action with a concrete parameter (date or period), matching the anchor for 1-2 concrete actions but not comprehensive; it omits theming, saving, and output formats, so it stays below 4 and above the minimal/generic level of 2.

3 / 5

Completeness

It answers both what ("Summarize AI conversation histories for a specified date or period") and when ("Use for daily work recaps and cross-tool activity summaries"), but the when clause is narrower than the skill's actual scope (no weekly/monthly triggers), fitting "'when' could be more explicit or specific" rather than 5.

4 / 5

Trigger Term Quality

"daily work recaps", "activity summaries", and "conversation histories" are phrases users would naturally say, giving good keyword coverage, but common variants like "weekly summary", "standup", or "work log" are missing, so it falls short of the comprehensive synonym coverage of 5.

4 / 5

Distinctiveness Conflict Risk

"AI conversation histories" carves a fairly distinct niche, but the generic words "recaps" and "summaries" carry minor overlap risk with related skills the body itself names (oma retro, oma stats), matching "mostly distinct; minor overlap risk" rather than the minimal-conflict clarity of 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.

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

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.