Total Skills
11
Author Profile: browzeremb
Skills published by browzeremb with real stars/downloads and source-aware metadata.
Total Stars
0
Total Downloads
0
Skills Performance
Comparison chart based on real stars and downloads signals from source data.
brainstorming
0
Stars
0
Downloads
0
code-review
0
Stars
0
Downloads
0
commit
0
Stars
0
Downloads
0
execute-task
0
Stars
0
Downloads
0
feature-acceptance
0
Stars
0
Downloads
0
generate-prd
0
Stars
0
Downloads
0
generate-task
0
Stars
0
Downloads
0
orchestrate-task-delivery
0
Stars
0
Downloads
0
Published Skills
brainstorming
Interactive clarification before any feature, spec, or design work — when the request lacks persona, success signal, or scope. Asks one grounded question at a time, informed by `browzer explore`/`search` on the actual repo, optionally dispatches parallel research agents (WebFetch, WebSearch, Firecrawl, Context7) for unknowns, hands off to generate-prd. Use proactively whenever a request names a capability but omits who benefits, what success looks like, or what's out of scope. Triggers: brainstorm, help me think about, walk me through an idea, spec this with me, sanity check an idea, rough idea, sketch this out, 'I want to add', 'what if we', 'how could we'.
Repository SourceNeeds Review
code-review
Post-implementation team review of a feature's diff. Spawns 4 mandatory agents in parallel — senior-engineer (cyclomatic complexity, DRY, clean code, best practices), software-architect (system design, race conditions, clean architecture, caching, performance), qa (regressions, edge cases, butterfly-effect breakage), regression-tester (runs scoped tests over modified files + their browzer deps) — plus domain specialists discovered via /find-skills. Every agent gets the diff + browzer deps (forward + reverse) + browzer mentions and may run browzer explore to detect prior art / duplication. Read-only — `receiving-code-review` applies fixes next. Triggers: code review, review this feature, audit my changes, review the diff, post-implementation review, team review, peer review, find issues in this PR.
Repository SourceNeeds Review
commit
Write a Conventional Commits v1.0.0 message mirroring the repo's last 5 commits, stamp the `on-behalf-of: @browzeremb` org-attribution trailer (per GitHub's organization-commit doc — orgs link via `on-behalf-of:`, NOT `Co-authored-by:` which is for human collaborators), and run `git commit`. Reports the SHA. Does NOT push. Use whenever the user wants to commit staged changes. Triggers: commit, commit this, save this, checkpoint, finish this task, ship this commit, write a commit message, conventional commit.
Repository SourceNeeds Review
execute-task
Implement one task end-to-end by dispatching domain specialists per its `task.explorer.skillsFound[]`. Each specialist loads project skills first, writes code scoped to `task.scope`, reports gates + invariants, and aggregates into `task.execution`. For free-form requests without a plan, calls `generate-task` first. Tests are NOT authored at this phase — they're written after `code-review` + `receiving-code-review` by the `write-tests` skill. Triggers: execute TASK_03, run the first task, implement task 02, do this task, ship TASK_N, build the feature from the plan, 'implement this'.
Repository SourceNeeds Review
feature-acceptance
Verify a finished feature against its PRD acceptance criteria, NFRs, and success metrics — autonomous mode (agent runs every check) or manual mode (operator runs a how-to-verify checklist out of band). Use before `commit` to confirm 'is this actually done?'. Triggers: feature acceptance, acceptance gate, verify acceptance criteria, check AC/NFR/metrics, 'is this feature ready', 'is the feature done', final verification, pre-commit acceptance, sign-off check.
Repository SourceNeeds Review
generate-prd
Produce a structured PRD for the current repo, grounded in real services + packages via `browzer explore`/`search` so requirements aren't fictional. Routes through `brainstorming` first when input is vague (no persona, no success signal, no scope). Use whenever defining, planning, or documenting any non-trivial feature, change, or refactor. Triggers: write a PRD, draft a PRD, PRD for, requirements doc, spec this out, document requirements for, plan this feature, turn this idea into a spec, roadmap this, sanity-check scope.
Repository SourceNeeds Review
generate-task
Two-pass task decomposer. Explorer pass (haiku, zero technical decisions) maps files, dep graphs, domains, and skills-to-invoke per prospective task; Reviewer pass (sonnet default, opus for complex scopes) validates the mapping and enumerates test coverage targets per task. Reads the PRD from `workflow.json`. Triggers: break this PRD into tasks, generate tasks, plan the implementation, decompose this spec, task plan, task breakdown, sequence the work, split this into PRs, 'how should I sequence this'.
Repository SourceNeeds Review
orchestrate-task-delivery
Master orchestrator for any feature, bugfix, or refactor that touches more than a few files in a Browzer-indexed repo. Drives the full pipeline: brainstorming (when vague) → PRD → task plan → execute → code-review → receiving-code-review → write-tests → update-docs → feature-acceptance → commit. Grounds decisions in `browzer explore`/`search`/`deps`; delegates all implementation to specialist subagents. Mid-workflow entry also welcome ('execute TASK_03', 'update the docs', 'commit what I staged'). Skip only for trivial ≤3-file read-only lookups. Triggers: build this, ship this end-to-end, implement this feature, refactor X, fix this bug, drive the workflow, run the dev pipeline, 'let's start'.
Repository SourceNeeds Review
receiving-code-review
Consumes `codeReview.findings[]` from the previous CODE_REVIEW step and dispatches per-domain fix agents until EVERY finding (high → low) reaches `status: fixed`. Each fix agent receives the finding body, the source file, browzer deps + mentions, and the relevant skill from `finding.assignedSkill`. Zero-tech-debt contract: a clean run leaves no open finding behind. Use after `code-review` and before `write-tests`. Triggers: receive code review, apply code review fixes, fix the findings, close the review, fix-findings, address review feedback, resolve code review.
Repository SourceNeeds Review
update-docs
Find every markdown doc whose accuracy depends on the just-changed code and patch it in place. Three signals: `browzer mentions` reverse traversal, direct-path-refs in markdown, and concept-level docs (CLAUDE.md invariants, ADRs, runbooks, READMEs) via `browzer deps --reverse` + `explore` + `search`. Patches existing docs only — never writes new ones. Triggers: update the docs, sync the documentation, docs are stale, refresh the README, propagate changes to docs, 'we changed X — what docs cover X'.
Repository SourceNeeds Review
write-tests
Author tests for a code change AND run mutation testing (Stryker / mutmut / go-mutesting) to verify the suite kills mutants. Each test is mutation-resistant by design — catches at least one plausible mutation (boolean, conditional, arithmetic, boundary, off-by-one, return-value). Auto-detects the repo's runner; skips when no test setup exists. Use after fixes land or for any 'cover these files' request. Triggers: write tests, add tests, test coverage for, unit tests for, test this, mutation testing, stryker, mutmut, kill mutants, 'tests for this change', spec these files.
Repository SourceNeeds Review