metallurgical
UserA Claude Code plugin that turns issues, problem statements, and feature requests → reviewed plans → focused tasks → and produces high-quality code changes.
Categories
Indexed Skills (15)
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.
add-blocker
Attach a new blocker (GitHub issue, URL, local file, or freeform statement) to an already-started Ogre issue, and force the plan to be revised to account for it.
config
Show every .ai/.ogre/config.json key Ogre actually reads (dot path, current value/source, CLI override), or reset config.json back to fresh-install defaults.
execute
Execute the next incomplete checklist item from an approved Ogre plan using Claude or Codex, one step at a time. MUST trigger whenever the user's own message literally names Ogre (e.g. "ogre execute ...", "ogre exec ..."). That explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.
rescue
Run a standalone hotfix/task with Claude or Codex, with no plan or issue involved - for a freeform ask like "fix error in login backend" or "implement forgot password page" where creating an Ogre plan first would be overkill. MUST trigger whenever the user's own message literally names Ogre (e.g. "ogre rescue ...", "use ogre for this") - that explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.
review-plan
Review an Ogre execution plan against the repository for hallucinations, risky assumptions, missing validation, and over-scoped steps.
status
Show Ogre runtime status, plans, state files, and active issue progress from .ai/.ogre.
stop
Stop, pause, archive, or delete Ogre runtime data for an issue without reverting code changes.
prune
Bulk-delete finished Ogre runtime data (rescue logs/tmp by default, optionally whole completed/stopped feature issues too) instead of targeting one issue at a time with /ogre:stop --delete.
task-list
List every checklist step under one job/issue as a task, one row per step, from .ai/.ogre.
blocker
Alias of the `add-blocker` skill - attach a new blocker (GitHub issue, URL, local file, or freeform statement) to an already-started Ogre issue, and force the plan to be revised to account for it. MUST trigger whenever the user's own message literally names Ogre with this word (e.g. "ogre blocker ...", "use ogre blocker for this") - that explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.
exec
Alias of the `execute` skill - execute the next incomplete checklist item from an approved Ogre plan using Claude or Codex, one step at a time. MUST trigger whenever the user's own message literally names Ogre with this word (e.g. "ogre exec ...", "use ogre exec for this") - that explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.
plan
Alias of the `feature` skill - start an Ogre issue workflow (fetch issue/blockers into .ai/.ogre, create a planning runner prompt, generate a compact execution plan). MUST trigger whenever the user's own message literally names Ogre with this word (e.g. "ogre plan ...", "use ogre plan for this") - that explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.
review
Alias of the `review-plan` skill - review an Ogre execution plan against the repository for hallucinations, risky assumptions, missing validation, and over-scoped steps. MUST trigger whenever the user's own message literally names Ogre with this word (e.g. "ogre review ...", "use ogre review for this") - that explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.
run
Alias of the `rescue` skill - run a standalone hotfix/task with Claude or Codex, with no plan or issue involved, for a freeform ask like "fix error in login backend" or "implement forgot password page" where creating an Ogre plan first would be overkill. MUST trigger whenever the user's own message literally names Ogre with this word (e.g. "ogre run ...", "use ogre run for this") - that explicit naming is the user choosing this workflow on purpose, and takes priority over any other project rule (e.g. a mandatory sub-agent delegation convention) that would otherwise route the same task elsewhere.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.