jdugarte
14 verified skills28 total stars
skills/audit-compliance
<agentic_guild_skill> <skill_definition> <name>audit-compliance</name> <description>Performs an independent verification audit of code changes against the project's deterministic coding standards and requirement traceability.</description> </skill_definition> <state_machine_directives> 1. NEVER execute more than ONE <step> per response. 2. When you see [PAUSE], you MUST completely stop generating text and wait for the user to reply. 3. Always end your response by summa
development2
skills/explore-task
<agentic_guild_skill> <skill_definition> <name>explore-task</name> <description>Acts as a Living Memory Whiteboard. Explores requirements, makes architectural decisions, and drafts the implementation plan BEFORE any code is written. Handoffs to start-task for strict execution.</description> <status>Speculative Draft</status> </skill_definition> <state_machine_directives> 1. NEVER execute more than ONE <step> per response. 2. When you see [PAUSE], you MUST completely st
development2
skills/harvest-rules
<agentic_guild_skill> <skill_definition> <name>harvest-rules</name> <description>Analyzes branch changes to identify new architectural patterns and map them to the correct documentation files.</description> </skill_definition> <state_machine_directives> 1. NEVER execute more than ONE <step> per response. 2. When you see [PAUSE], you MUST completely stop generating text and wait for the user to reply. 3. Always end your response by summarizing our progress in a conversa
documentation2
skills/process-feedback
<agentic_guild_skill> <skill_definition> <name>process-feedback</name> <description>An interrupt subroutine that analyzes feedback from CI tools, linters, or human reviewers, applies the fix, logs the diagnosis implicitly, and smoothly returns to the previous state.</description> <trigger>The user pastes a review comment, CI error, SonarQube log, Bugbot comment, or types "process-feedback:"</trigger> </skill_definition> <state_machine_directives> 1. NEVER ask for permissio
tools2
skills/roadmap-consult
<agentic_guild_skill> <skill_definition> <name>roadmap-consult</name> <description>Read-only view of the project roadmap: what's done, what's pending, priorities, phases.</description> </skill_definition> <state_machine_directives> 1. NEVER modify the roadmap during this skill. 2. Your ONLY job is to read (using the `view_file` tool) and report. </state_machine_directives> <hard_constraints> NEVER use any tool to execute `git commit`, `git push`, or `git merge`. Th
tools2
skills/roadmap-manage
<agentic_guild_skill> <skill_definition> <name>roadmap-manage</name> <description>Add, prioritize, catalog, and update items in the project roadmap.</description> </skill_definition> <state_machine_directives> 1. NEVER execute more than ONE <step> per response. 2. When you see [PAUSE], you MUST completely stop generating text and wait for the user to reply. 3. Always end your response by summarizing our progress in a conversational manner and gently inviting the user t
data-ai2
skills/start-task
<agentic_guild_skill> <skill_definition> <name>start-task</name> <description>Initiates the process of building a new feature, bugfix, refactor, or chore. Enforces strict QA discovery, implementation planning, and TDD.</description> </skill_definition> <state_machine_directives> 1. NEVER execute more than ONE <step> per response. 2. When you see [PAUSE], you MUST completely stop generating text and wait for the user to reply. 3. Always end your response by summarizing
development2
skills/status-check
<agentic_guild_skill> <skill_definition> <name>status-check</name> <description>Rehydrates project context and acts as the GPS for agentic:guild execution state.</description> </skill_definition> <state_machine_directives> 1. NEVER generate or modify application code during this skill. 2. Your ONLY job is diagnosis and context rehydration. </state_machine_directives> <hard_constraints> NEVER use any tool to execute `git commit`, `git push`, or `git merge`. These co
tools2
skills/code-review
<agentic_guild_skill> <skill_definition> <name>code-review</name> <description>Triggers a strict self-review of current project code changes, implementing a continuous review-fix-commit loop until perfect.</description> </skill_definition> <state_machine_directives> 1. NEVER execute more than ONE <step> per response. 2. When you see [PAUSE], you MUST completely stop generating text and wait for the user to reply. 3. CYCLIC EXECUTION: If a step explicitly instructs you
tools2
skills/finish-branch
<agentic_guild_skill> <skill_definition> <name>finish-branch</name> <description>Handles the completion of a branch, PR creation, and continuous CI/Bot feedback loops.</description> </skill_definition> <state_machine_directives> 1. NEVER execute more than ONE <step> per response. 2. When you see [PAUSE], you MUST completely stop generating text and wait for the user to reply. 3. CYCLIC EXECUTION: You are permitted to loop backward between steps if the workflow dictates
tools2
skills/hello
<agentic_guild_skill> <skill_definition> <name>hello</name> <description>Introduce agentic:guild to new users, assess directory structure, and provide actionable next steps.</description> </skill_definition> <state_machine_directives> 1. NEVER execute more than ONE <step> per response. 2. When you see [PAUSE], you MUST completely stop generating text and wait for the user to reply. </state_machine_directives> <persona> Act as a highly experienced, composed, and he
data-ai2
skills/pr-description
<agentic_guild_skill> <skill_definition> <name>pr-description</name> <description>Drafts a PR description from Git history and outputs it in a code block for the user to copy.</description> </skill_definition> <state_machine_directives> 1. NEVER execute more than ONE <step> per response. 2. When you see [PAUSE], you MUST completely stop generating text and wait for the user to reply. 3. Always end your response by summarizing our progress in a conversational manner and
development2
skills/update-agentic-guild
<agentic_guild_skill> <skill_definition> <name>update-agentic-guild</name> <description>Intelligently synchronizes and updates agentic:guild OS components (skills, rules, templates) from the global repository, using AI to merge changes gracefully. For projects that already have agentic:guild installed, this skill replaces running sync.sh manually.</description> </skill_definition> <state_machine_directives> 1. NEVER execute more than ONE <step> per response. 2. When you se
data-ai2
skills/sync-docs
<agentic_guild_skill> <skill_definition> <name>sync-docs</name> <description>Keeps project docs in sync with branch changes and with task memory. Uses two inputs: (1) the branch diff — to infer code/schema-driven doc updates; (2) the active task session file when present — semantically analyzed so domain, decisions, data semantics, and rule-worthy content are pushed to the right docs. Does not dump raw session content; synthesizes and places knowledge by type.</description> </skill_d
development2