CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

checkpoint

Use when about to start risky changes, before major refactors, or when you need a safe rollback point during multi-step implementations.

Quality

60%

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 ./skills/checkpoint/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 highly actionable with executable git commands for every subcommand and clean single-file organization. Its weaknesses are moderate token redundancy (repeated workflow examples, sample output blocks, duplicated clean sections) and missing validation/verification around the destructive reset and batch tag-deletion operations, which caps workflow clarity.

Suggestions

Add validation around destructive and batch operations: verify the tag exists before 'git reset --hard', run 'git status' after restore to confirm the state, and show a count/dry-run (e.g. 'git tag -l "checkpoint/*" | wc -l') before deleting tags.

Trim redundancy: drop the generic trailing '## Output' section, fold 'Usage in Workflow' examples into the operation sections they repeat, and merge 'Clean Checkpoints' and 'Clean All' into one section with a scope flag.

Shorten or remove the fabricated output blocks (fake timestamps like '2024-01-15 14:30:22') — a one-line description of the expected result format conveys the same information in far fewer tokens.

DimensionReasoningScore

Conciseness

Concrete commands with no over-explanation of git concepts, but it could be tightened: the trailing generic '## Output' section, 'Usage in Workflow' re-demonstrating already-defined operations, fabricated output blocks ('Time: 2024-01-15 14:30:22'), and near-duplicate clean/clean-all sections add tokens.

3 / 5

Actionability

Every operation has copy-paste-ready commands ('git add -A', 'git commit -m "checkpoint: [name]"', 'git tag checkpoint/[name]', 'git tag -l "checkpoint/*" | xargs -n 1 git tag -d', 'git reset --hard checkpoint/[name]') covering create, restore-point, list, restore, rollback, clean, and default behavior.

5 / 5

Workflow Clarity

Sequences per operation are clear and restore carries a 'Confirm with user first' note, but the destructive ('git reset --hard') and batch (xargs tag deletion) workflows lack verification steps — no tag-exists check before reset, no post-reset 'git status', no dry-run count before clean — so the destructive/batch cap applies.

3 / 5

Progressive Disclosure

A single-file command skill with no bundle files and no need for external references; sections map one-to-one onto subcommands (Create, Restore Point, List, Restore, Rollback, Clean) with clear headers, making navigation easy.

5 / 5

Total

16

/

20

Passed

Description

31%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 entirely trigger-focused: it gives three explicit 'when' scenarios but omits any statement of what the skill actually does, and it never mentions git or checkpoints. Rewriting it in third person with both a capability list and checkpoint/git trigger terms would substantially improve it.

Suggestions

State the 'what' explicitly in third person, e.g. 'Creates, restores, lists, and cleans git checkpoints (commit + tag save points) to enable safe rollbacks during development.'

Add the natural trigger terms users would actually say — 'checkpoint', 'save point', 'snapshot', 'git', 'rollback' — so the skill matches requests phrased in those words.

Remove the second-person construction ('when you need a safe rollback point') and rephrase in third person to comply with the expected description voice.

DimensionReasoningScore

Specificity

The description contains only trigger scenarios ('about to start risky changes', 'before major refactors', 'safe rollback point') and never states what the skill does — create, restore, list, or clean git checkpoints — matching the 'actions are minimal or generic' anchor at 2, reduced by 1 for the second-person 'when you need a safe rollback point' per the voice rule.

1 / 5

Completeness

Only 'when' is present without 'what': three explicit usage triggers exist, but the description never says what the skill does, an exact match for anchor 2; it cannot score 3 because that anchor requires a clear 'what'.

2 / 5

Trigger Term Quality

Some relevant natural phrases are present ('risky changes', 'major refactors', 'rollback point'), but the most likely user terms — 'checkpoint', 'git', 'snapshot', 'save point' — are entirely absent, matching 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

'Risky changes' and 'major refactors' are somewhat specific to the pre-change safety niche, but without 'git' or 'checkpoint' in the description it could overlap with generic backup, undo, or refactoring-safety skills, matching 'somewhat specific but could still overlap with similar skills'.

3 / 5

Total

9

/

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

fernandezbaptiste/specialist-agent

Path

skills/checkpoint/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.