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

73%

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 ./skills/oma-recap/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 strongly operational skill body with executable commands, thoughtful failure handling, and precise output rules. Its main defects are duplicated guidance across the Scheduling and Process sections, and a broken bundle: the referenced templates file is missing, which weakens both the format validation checkpoint and the progressive-disclosure structure.

Suggestions

Ship the missing 'resources/output-formats.md' (or move it to a standard 'references/' directory) so the daily and multi-day templates actually resolve; a dangling reference is worse than inlining the templates.

De-duplicate the CLI-fallback and date/window rules, which appear in both 'Transitions' and the 'Process' steps — state each rule once and cross-reference it.

Rename or tighten the 'Scheduling' section: it currently wraps the entire skill (goal, intent, process) rather than scheduling-specific content, adding meta-overhead to the token budget.

DimensionReasoningScore

Conciseness

The body is dense and operational — exact commands, a complete jq fallback with macOS/Linux variants, and numbered rules — with no explanations of concepts Claude already knows. It is not a 5 because content repeats across sections: the CLI-fallback and date/window rules appear in both 'Transitions' and the 'Process' steps, and the 'Scheduling' meta-section restates scope already covered later.

4 / 5

Actionability

Commands are copy-paste ready ('oma recap --date YYYY-MM-DD --json', the full jq pipeline with DST-safe timestamp handling) and the 10 guardrails concretely specify output structure (TL;DR = top 3 outcomes, time-range format, 2-4 bullets). The gap keeping it below 5 is that the actual output templates are delegated to 'resources/output-formats.md', so the exact deliverable format cannot be reproduced from the skill alone.

4 / 5

Workflow Clarity

A clear 5-step canonical path with explicit transitions, a dedicated failure-and-recovery section, and defined exit criteria (success / partial success) — matching 'Clear sequence with most checkpoints present'. It misses anchor 5 because the one explicit validation step ('check it against that template') depends on a template file that is not in the bundle, leaving the final checkpoint unverifiable.

4 / 5

Progressive Disclosure

The bundle contains no resource files at all, yet the body references 'resources/output-formats.md' in section 4 and in References — a dangling path that does not exist. Inline structure is well organized, but the intended split (templates in a separate file) is not actually realized, fitting 'Some structure ... references present but not clearly signaled' territory rather than the good-structure level of 4.

3 / 5

Total

15

/

20

Passed

Description

62%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 two-sentence description with the right what/when shape and third-person voice. Its weaknesses are thin action coverage (only 'Summarize') and missing natural trigger terms like weekly summary, standup, or work log that the skill body itself identifies.

Suggestions

List 2-3 concrete actions instead of one, e.g. 'Summarize AI conversation histories for a date or period, group them by project and theme, and save a Markdown recap.'

Add natural trigger terms the body already recognizes: 'Use when the user asks for a daily recap, weekly summary, standup notes, or work log.'

Name the oma CLI or scope boundary to reduce overlap with adjacent commands like 'oma retro' and 'oma stats'.

DimensionReasoningScore

Specificity

The description names a clear domain ("AI conversation histories for a specified date or period") but only one concrete action ("Summarize"), comparable to 'Processes PDF files and extracts content'. It omits concrete capabilities the body covers (themed/project grouping, tool-usage patterns, saved Markdown output), so it does not reach the 'several specific actions' level of 4.

3 / 5

Completeness

Both parts are present: what ("Summarize AI conversation histories for a specified date or period") and an explicit when ("Use for daily work recaps and cross-tool activity summaries"). It falls short of anchor 5 because the trigger phrases are limited to two and "cross-tool activity summaries" is more abstract than the concrete, varied triggers in the anchor-5 example.

4 / 5

Trigger Term Quality

"daily work recaps" and "Summarize ... conversation histories" are natural phrases users would say, but common variations are missing — the body itself lists "standup notes", "work log", and "weekly/monthly summary" as intents, none of which appear in the description. This matches 'Some relevant keywords but missing common variations or synonyms' rather than the good-coverage level of 4.

3 / 5

Distinctiveness Conflict Risk

"AI conversation histories" plus "cross-tool" defines a clear niche unlikely to collide with unrelated skills, matching 'Mostly distinct; minor overlap risk'. It is not a 5 because generic sibling commands (oma retro, oma stats) cover adjacent summarization territory and the description does not name the distinguishing tool (oma) or scope boundary.

4 / 5

Total

14

/

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

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.