CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

catchup

Restore context after /clear by summarizing recent work and project state

60

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./examples/skills/catchup/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a well-structured, executable recipe: four sequenced git-inspection steps with real commands and a concrete output template, all appropriately contained in one file. Its weaknesses are minor — redundant framing text and advertised argument variants that the instructions never define.

Suggestions

Drop or merge the 'Purpose' section and the opening line, which restate the frontmatter description and add tokens without new information.

Either implement the advertised argument modes or remove them: '/catchup --brief', '/catchup auth', and the '[branch] [--since <date>]' hint have no corresponding instructions, so tell Claude exactly how to filter or summarize differently for each.

Harden the Step 3 TODO scan for filenames with spaces (e.g., use 'git grep -n -e TODO -e FIXME -- $(git diff --name-only HEAD~5)' or '-z' with xargs -0) so the flagship command is robust.

DimensionReasoningScore

Conciseness

The body is dominated by lean, commented bash blocks with no explanations of concepts Claude already knows, matching anchor 4 ('efficient; minor instances of over-explanation that could be trimmed'). It misses anchor 5 because the 'Purpose' section and opening line restate the frontmatter description, and the emoji-decorated output template carries some padding.

4 / 5

Actionability

Steps 1-4 provide concrete, copy-paste-ready bash commands and the Output format is an explicit fill-in template, matching anchor 4 ('mostly executable guidance... with minor gaps'). Not anchor 5 because the Usage examples promise '/catchup --brief' and '/catchup auth' modes (and the argument-hint advertises '[branch] [--since <date>]') that no instruction actually implements, and the TODO-scan pipeline breaks on filenames with spaces.

4 / 5

Workflow Clarity

The four steps are clearly sequenced (history analysis → recent changes → TODO scan → project state) and the operation is read-only, so the destructive/batch validation cap does not apply. It matches anchor 4 ('clear sequence with most checkpoints present; minor validation gaps') but not 5, since the advertised argument modes (--brief, branch filter, --since) are undefined in the instructions, leaving an execution gap.

4 / 5

Progressive Disclosure

There are no bundle files and none are needed: this self-contained, single-task skill keeps all content appropriately inline under a clean hierarchy (Purpose, Instructions with four labeled steps, Output format, Usage examples, Pro tips), making navigation trivial. Per the simple-skill scoring note, well-organized sections with no need for external references warrant a 5.

5 / 5

Total

17

/

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.

The description is clear, honest, and correctly scoped: it states what the skill does and gives one explicit, distinctive trigger (/clear). Its main weaknesses are thin action coverage and missing natural trigger variations, leaving it solid but not exemplary.

Suggestions

Enumerate the concrete actions to raise specificity, e.g., 'Restore context after /clear by summarizing recent commits, uncommitted changes, outstanding TODOs, and project state.'

Broaden trigger terms to the phrases users naturally say, such as 'catch up', 'what was I working on', or 'resume work after clearing context', moving from a single '/clear' trigger toward comprehensive coverage.

Make the 'when' clause more explicit and complete (e.g., 'Use after /clear, at session start, or when resuming work on a project') so both what and when are fully concrete.

DimensionReasoningScore

Specificity

The description names its domain ("Restore context after /clear") and 1-2 concrete actions ("summarizing recent work and project state"), but stops short of the several specific actions the skill actually performs (TODO scanning, branch/state checks, next-step suggestions). It matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') rather than 4, which requires a fuller list of specific actions.

3 / 5

Completeness

Both parts are answered: what ("summarizing recent work and project state" to "Restore context") and when ("after /clear") — the when is explicitly stated, so this is above anchor 3 ('when missing or only weakly implied'). It falls short of anchor 5 because the trigger guidance is a single embedded condition rather than comprehensive concrete trigger phrases (e.g., no 'or at session start', 'when resuming work').

4 / 5

Trigger Term Quality

"/clear" is a natural, precise trigger term and "recent work" / "project state" are relevant, but common user phrasings like "catch up", "what was I working on", or "session start" are absent. Some relevant keywords with missing variations matches anchor 3, not 4 ("good keyword coverage; a few natural terms missing" would require broader coverage).

3 / 5

Distinctiveness Conflict Risk

"Restore context after /clear" carves out a clear niche with a distinct trigger unlikely to fire for unrelated skills, matching anchor 4 ('mostly distinct; minor overlap risk'). Not anchor 5 because context-restoration could mildly overlap with memory/summary-style skills and the trigger set is narrow rather than unmistakably distinct.

4 / 5

Total

14

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

FlorianBruniaux/claude-code-ultimate-guide

Path

examples/skills/catchup/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.