CtrlK
BlogDocsLog inGet started
Tessl Logo

bitbucket-automation

Automate Bitbucket repositories, pull requests, branches, issues, and workspace management via Rube MCP (Composio). Always search tools first for current schemas.

76

1.33x
Quality

68%

Does it follow best practices?

Impact

88%

1.33x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/bitbucket-automation/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 highly actionable, well-sequenced operational reference with exact tool names, parameters, and pitfall callouts that make workflows executable. Its weaknesses are duplicated pitfall content that inflates token cost and a monolithic single-file structure where per-domain references would improve navigation.

Suggestions

Split per-domain detail (PR workflows, issues, branches, quick-reference table) into one-level-deep reference files (e.g., references/pull-requests.md, references/issues.md) and keep SKILL.md as an overview with clearly signaled links.

Deduplicate the pitfalls: state each pitfall once (e.g., BBQL double-quoting appears in three places) and consolidate the "Known Pitfalls" section to only cross-cutting items not already covered in workflows.

Add post-operation validation steps and a validate-fix-retry loop for batch operations (e.g., verify PR state after creation, re-check pagination via the `next` URL before finishing a listing).

DimensionReasoningScore

Conciseness

The body is dense reference material with no explanation of concepts Claude already knows, but contains notable redundancy: BBQL double-quoting rules appear three times, and the "irreversible delete", "assignee vs assignee_account_id", and destination_branch-default pitfalls are each duplicated between workflow sections and the "Known Pitfalls" section. This fits 'mostly efficient but could be tightened' rather than 4's 'minor instances'.

3 / 5

Actionability

Fully executable, instruction-only guidance: exact tool slugs, concrete parameter names and formats (`[{"uuid": "{...}"}]`, `name~"api"`, `"on hold"`), enumerated value sets, and a per-task quick-reference table. Not 4: the common cases (create PR, comment, filter, paginate) are covered with copy-paste-ready specifics rather than having minor gaps.

5 / 5

Workflow Clarity

Each workflow is a clearly numbered sequence with [Prerequisite]/[Required]/[Optional] markers, setup includes an explicit checkpoint ("Confirm connection status shows ACTIVE"), and destructive operations are gated ("Always confirm with the user before executing delete operations"). Not 5: there are no post-operation verification steps or validate-fix-retry feedback loops, and batch/rate-limit guidance lacks any loop, leaving minor validation gaps.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), so the entire ~230-line per-tool reference — five workflow breakdowns, pitfalls, and a 17-row quick-reference table — is inlined in one file. Section headers give it structure, but this is exactly the content that belongs in one-level-deep reference files, matching 'content that should be separate is inline'.

3 / 5

Total

15

/

20

Passed

Description

66%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 specific, well-scoped description that names the platform and enumerates concrete capability areas with good natural trigger terms. Its main weakness is the complete absence of a 'when to use' clause, which caps completeness, and slight reliance on one generic action verb.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions Bitbucket, wants to create or review Bitbucket pull requests, manage Bitbucket repos/branches/issues, or automate Bitbucket workspace tasks."

Broaden natural trigger terms with common synonyms such as "PRs", "code review", and "merge" so the description matches how users actually phrase these requests.

Consider naming one or two more granular actions (e.g., "comment on PRs", "review diffs") to move from one umbrella verb to multiple concrete actions.

DimensionReasoningScore

Specificity

Enumerates five concrete capability areas ("repositories, pull requests, branches, issues, and workspace management") under the action verb "Automate". It falls short of 5 because a single action verb covers them all, and exceeds 3 because the coverage is several specific capabilities, not 1-2.

4 / 5

Completeness

The "what" is clear ("Automate Bitbucket repositories, pull requests, branches, issues, and workspace management via Rube MCP"), but there is no "Use when..." clause or equivalent trigger guidance; "Always search tools first for current schemas" is procedural instruction, not a trigger. Per the rubric guideline, a missing trigger caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms users would say are present: "Bitbucket", "pull requests", "repositories", "branches", "issues", "workspace". Not 5 because common variations like "PRs", "code review", or "merge" are missing; well above 3's partial keyword coverage.

4 / 5

Distinctiveness Conflict Risk

"Bitbucket" and "Rube MCP (Composio)" pin a clear niche with minimal conflict risk. Not 5 because generic terms like "pull requests" and "branches" carry minor overlap risk with other git-platform skills; clearly above 3's 'could still overlap with similar skills'.

4 / 5

Total

15

/

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
davepoon/buildwithclaude
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.