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.

54

Quality

61%

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/bitbucket-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a comprehensive Bitbucket automation skill that covers the major workflows well with specific tool names, parameters, and useful pitfall warnings. Its main weaknesses are significant content repetition (pitfalls duplicated across sections), lack of validation steps integrated into destructive operation workflows, and a monolithic structure that would benefit from splitting into overview + reference files. Trimming the duplicated content and adding explicit confirmation steps for delete operations would meaningfully improve quality.

Suggestions

Consolidate duplicated pitfalls — remove per-workflow pitfall entries that are repeated verbatim in the 'Known Pitfalls' section, or vice versa, to reduce token usage by ~30%.

Add explicit user confirmation steps directly into the workflow sequences for DELETE_REPOSITORY and DELETE_ISSUE (e.g., 'Step N: Confirm with user before proceeding — this is irreversible').

Split the detailed parameter lists, pitfalls, and quick reference table into a separate REFERENCE.md file, keeping SKILL.md as a concise overview with tool sequences and key gotchas only.

Add at least one concrete example of a full tool invocation with parameters (e.g., a complete RUBE_SEARCH_TOOLS call followed by a BITBUCKET_CREATE_PULL_REQUEST call with all required params filled in).

DimensionReasoningScore

Conciseness

The skill is quite long (~200+ lines) with significant repetition. Pitfalls are repeated across individual workflow sections and then again in a consolidated 'Known Pitfalls' section (e.g., BBQL double quotes, assignee vs assignee_account_id, destructive operations). The quick reference table largely duplicates information already covered in the workflows. However, the content itself is domain-specific and not explaining things Claude already knows.

3 / 5

Actionability

The skill provides concrete tool names, specific parameter names and values, and clear tool sequences for each workflow. It lacks executable code examples (no actual MCP call syntax shown), but for an MCP tool-based skill, the tool slugs and parameter specifications are sufficiently concrete and actionable. Minor gap: no example of an actual tool invocation with full parameters.

4 / 5

Workflow Clarity

Workflows are clearly sequenced with numbered steps and labeled as Required/Optional/Prerequisite. However, destructive operations (DELETE_REPOSITORY, DELETE_ISSUE) lack explicit validation/confirmation steps in the workflow sequences themselves — the guidance to 'confirm with the user' is buried in the Known Pitfalls section rather than integrated into the workflow steps. Per rubric rules, missing validation for destructive operations caps this at 3.

3 / 5

Progressive Disclosure

The content is entirely monolithic with no bundle files or references to external documents. At ~200+ lines with detailed parameter lists, pitfalls sections, and a full reference table, this would benefit from splitting detailed parameter documentation and pitfalls into separate reference files. The internal structure (headers, sections) is reasonable but the volume of content in a single file is excessive.

3 / 5

Total

13

/

20

Passed

Description

66%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 does a reasonable job identifying the domain (Bitbucket) and listing key entities it manages, with good distinctiveness from similar VCS skills. Its main weaknesses are the lack of an explicit 'Use when...' trigger clause and the use of the vague verb 'automate' instead of listing concrete actions like creating PRs, merging branches, or reviewing code.

Suggestions

Add an explicit 'Use when...' clause with trigger phrases, e.g., 'Use when the user asks about Bitbucket repos, pull requests, branches, or workspace management.'

Replace the vague 'Automate' with specific actions such as 'Create, review, and merge pull requests; manage branches and repositories; track issues.'

Include common synonyms and abbreviations users might use, such as 'PRs', 'repos', 'merge', 'code review', 'Bitbucket Cloud'.

DimensionReasoningScore

Specificity

Lists several specific entities (repositories, pull requests, branches, issues, workspace management) and mentions the tooling context (Rube MCP / Composio). However, the actual actions are somewhat vague—'automate' is broad and doesn't specify concrete operations like 'create PR', 'merge branches', etc.

4 / 5

Completeness

The 'what' is reasonably clear (automate Bitbucket operations via Composio), but there is no explicit 'when' clause. The instruction to 'always search tools first' is operational guidance rather than a trigger condition. The lack of a 'Use when...' clause caps this at 3.

3 / 5

Trigger Term Quality

Includes strong natural keywords like 'Bitbucket', 'repositories', 'pull requests', 'branches', 'issues', and 'workspace'. Missing some common synonyms or variations users might say (e.g., 'PRs', 'repos', 'merge', 'clone', 'code review').

4 / 5

Distinctiveness Conflict Risk

Specifying 'Bitbucket' and 'Rube MCP (Composio)' makes it fairly distinct from generic Git or GitHub skills. Minor overlap risk exists with other version control or repository management skills, but the Bitbucket + Composio combination narrows the niche well.

4 / 5

Total

15

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.