CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rebase

Rebase an OpenMeter branch onto another branch and handle repo-specific gotchas like sequential migrations, atlas.sum conflicts, Ent regeneration, and targeted verification.

Quality

80%

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 ./.agents/skills/rebase/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tightly written, highly actionable skill body: every section carries exact commands, file paths, and repo-specific guardrails, with a real verification step and error-recovery guidance. Its only weaknesses are minor — slight redundancy in the "Why" prose and no post-recreation sequentiality check.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence ("Check `git status --short --branch` first", "Never hand-edit `openmeter/ent/db/`") with no explanation of concepts Claude already knows. Minor trimmable padding remains: the "Why:" bullet list and "In practice, regenerating first resolves or clarifies most conflicts much faster..." restate the same point as the preceding instruction. Not a 3 since excess is limited to one section; not a 5 since that section is mildly redundant.

4 / 5

Actionability

Every section gives copy-paste-ready, executable commands: `make generate`, `atlas migrate --env local hash`, `atlas migrate --env local diff <migration-name>`, `nix develop --impure .#ci -c <command>`, and `POSTGRES_HOST=127.0.0.1 go test -tags=dynamic ./openmeter/ledger/...`, plus exact file paths (`.up.sql`/`.down.sql` pairs, `tools/migrate/migrations/atlas.sum`, `openmeter/ent/schema/*.go`). The common cases are covered concretely with no pseudocode.

5 / 5

Workflow Clarity

The standard flow and migration flow are numbered and ordered, and there is an explicit validation step ("run the smallest relevant test slice for the touched area") with error-triage guidance ("If there is a known pre-existing failure, call it out explicitly and separate it from any new regression"). Regeneration-first is a feedback loop for conflicts. Not a 5 because there is no explicit post-recreation check that migrations are sequential and no guidance on what to do if `atlas migrate hash` itself fails.

4 / 5

Progressive Disclosure

The single-file body is well organized into clear sections ("Before rebasing", "Standard flow", "Migration conflicts", "atlas.sum conflicts", "Verification") with no nested or buried references, and nothing clearly belongs in a separate file. Not a 5 because at ~115 lines it exceeds the under-50-line simple-skill carve-out, and areas like the migration-recreation flow could be split into a reference file to keep SKILL.md a leaner overview.

4 / 5

Total

17

/

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 strong, specific description that clearly communicates what the skill does and is tightly scoped to the OpenMeter repository, minimizing conflict risk. Its main weakness is the absence of any 'Use when...' trigger clause, which leaves the 'when to use it' half of completeness implicit.

Suggestions

Append an explicit trigger clause, e.g. "Use when rebasing or updating an OpenMeter branch, especially onto origin/main, or when migration, Ent, or generated-code conflicts appear during a rebase."

Add natural trigger variations users might say, such as "git rebase" and "merge/migration conflicts", to broaden keyword coverage.

Lead the capability list with verb-led actions (e.g. "Resolves atlas.sum conflicts, regenerates Ent code, recreates out-of-order migrations") to sharpen the what.

DimensionReasoningScore

Specificity

Quotes: "Rebase an OpenMeter branch onto another branch", "handle repo-specific gotchas like sequential migrations, atlas.sum conflicts, Ent regeneration, and targeted verification" — the domain and several concrete capability areas are named explicitly. Not a 5 because the actions are framed as a list of gotchas rather than multiple discrete verb-led actions, and coverage of what 'handling' entails is not comprehensive.

4 / 5

Completeness

Quotes: "Rebase an OpenMeter branch onto another branch and handle repo-specific gotchas..." — the 'what' is clear and concrete, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 4 because 'when' is entirely absent rather than merely implicit or underspecific.

3 / 5

Trigger Term Quality

Quotes: "Rebase", "branch", "migrations", "conflicts" — these are natural terms a user would say when needing this skill. Not a 5 because common variations like "git rebase", "merge conflict", or "conflict resolution" are absent; not a 3 because the core natural vocabulary is present and specific.

4 / 5

Distinctiveness Conflict Risk

Quotes: "OpenMeter branch", "sequential migrations, atlas.sum conflicts, Ent regeneration" — the description is scoped to one specific repository and its named tooling, giving it a clear niche with distinct triggers and minimal conflict risk with generic git or migration skills.

5 / 5

Total

16

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository

openmeterio/openmeter

Path

.agents/skills/rebase/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.