bmad-generate-project-context

Create project-context.md with AI rules. Use when the user says "generate project context" or "create project context"

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./src/bmm-skills/3-solutioning/bmad-generate-project-context/SKILL.md

Quality

Content

50%

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

The body is well-structured as an activation/orchestration overview that defers detail to step files, which is the right shape. Its weaknesses are placeholder-driven steps that are not directly executable and the missing steps/ bundle, which undercuts both actionability and verified progressive disclosure.

Suggestions

Replace template-placeholder steps (e.g. 'Execute each entry in {workflow.activation_steps_prepend}') with a worked example or a note stating values are runtime-resolved, so the body reads as concrete guidance.

Include the steps/ directory (at minimum step-01-discover.md) so the single referenced navigation target actually exists and progressive disclosure can be verified.

Add an explicit validation checkpoint (e.g. confirm the resolved workflow block is non-empty and well-formed) before proceeding to the main workflow, raising the feedback-loop rigor for this orchestration skill.

Dimension	Reasoning	Score
Conciseness	Most content is directive and assumes competence (e.g. merge-rule shorthand), but the Conventions block and several Activation substeps restate resolver mechanics and template resolution that could be tightened or delegated to the referenced scripts.	2 / 3
Actionability	It gives a concrete executable command (the resolve_customization.py invocation) and explicit merge rules, but most steps are template placeholders like 'Execute each entry in {workflow.activation_steps_prepend}' that cannot be run as written without the resolved config.	2 / 3
Workflow Clarity	The activation sequence (Steps 1-6) is clearly numbered with a user-approval checkpoint, but validation/verification is limited to 'if the script fails' fallback handling; no explicit validate-and-confirm feedback loop gates the main workflow entry.	2 / 3
Progressive Disclosure	It correctly delegates the main work to steps/step-01-discover.md (one level deep), but the steps/ bundle directory is absent from the skill, so the primary referenced path cannot be verified to exist, leaving navigation only partially sound.	2 / 3
	Total	8 / 12 Passed

Description

82%

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 clearly answers both what it does and when to use it with natural, copy-paste-ready trigger phrases, which is its strongest aspect. Specificity and distinctiveness are merely adequate because it lists only one action and could be confused with other context-generation skills.

Suggestions

Add one or two more concrete actions (e.g. 'capture implementation rules and patterns') to lift specificity from a single verb to a fuller capability list.

Sharpen the niche to reduce conflict risk, e.g. 'Create a project-context.md of unobvious implementation rules for AI coding agents' rather than generic 'AI rules'.

Dimension	Reasoning	Score
Specificity	It names the domain (project-context.md, AI rules) and a concrete artifact, but only lists one action ('Create') without enumerating the multiple concrete capabilities involved.	2 / 3
Completeness	It explicitly answers what ('Create project-context.md with AI rules') and when ('Use when the user says "generate project context" or "create project context"'), satisfying both halves with an explicit trigger clause.	3 / 3
Trigger Term Quality	Quotes the natural user phrases 'generate project context' and 'create project context', which are exactly what a user would say to invoke this skill.	3 / 3
Distinctiveness Conflict Risk	'project-context.md' and AI rules are a recognizable niche, but the phrasing overlaps with broader context-generation skills and lacks further disambiguating detail, so conflict risk remains moderate.	2 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: bmad-code-org/BMAD-METHOD
Path: src/bmm-skills/3-solutioning/bmad-generate-project-context/SKILL.md
Commit: bb45db4

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.