Borda
UserA collection of personal AI coding assistant configurations, specialist agents, and automated workflows optimized for Python and ML open-source development.
Categories
Indexed Skills (47)
debug
Investigation-first debugging — gather evidence, form confirmed root-cause hypothesis, hand off to fix mode with diagnosis file. TRIGGER when: user reports a symptom or failing test with Python traceback, or asks to investigate a runtime/CI failure with reproducible evidence; phrases: "debug this failure", "why is X broken", "find the root cause of <error>", "investigate this CI failure". SKIP when: pure config quality issues (use `/foundry:audit`); broad system-wide diagnosis without traceback (use `/foundry:investigate`); user already knows the fix (use `/develop:fix`); non-Python project.
feature
TDD-first feature development — crystallise API as a demo test, drive implementation to pass it, run quality stack and progressive review loop. TRIGGER when: user asks to build new functionality, add a capability, or implement a feature in a Python project; phrases: "add X", "implement Y", "build Z feature", "create a new module for". SKIP when: bug fixes (use `/develop:fix`); refactoring without new behaviour (use `/develop:refactor`); non-Python projects; `.claude/` config changes (use `/foundry:manage`).
fix
Reproduce-first bug resolution — capture bug in failing regression test, apply minimal fix, run quality stack and review loop. TRIGGER when: user reports a bug, regression, or unexpected behaviour in Python code with a traceback, failing test, or issue number; phrases: "fix this bug", "repair X", "broken since Y", "test failing". SKIP when: CI-only failures without local traceback (use `/develop:debug` first); new features (use `/develop:feature`); `.claude/` config issues (use `/foundry:audit`); non-Python projects.
plan
Interactive wizard that scans the codebase, proposes a metric/guard/agent config, and writes a program.md run spec. Also runs cProfile on a file path to surface bottlenecks before prompting for optimization goal.
refactor
Test-first refactoring — audit coverage, add characterization tests, apply changes with safety net, run quality stack and review loop. TRIGGER when: user wants to restructure existing Python code without changing behaviour; phrases: "refactor X", "clean up Y", "extract Z", "restructure this module", "improve code quality". SKIP when: bug fixes (use `/develop:fix`); new features (use `/develop:feature`); mixed refactor+feature — run `/develop:refactor` first, then `/develop:feature`; non-Python projects.
brainstorm
Iterative brainstorming skill for turning fuzzy ideas into approved tree documents. Diverges into branches, deepens and prunes them over many rounds, saves a tree doc. Run breakdown on the tree to distill it into a spec via guided questions.
create
Interactive outline co-creation for developer advocacy content — collects format, audience profile, story arc (Problem→Journey→Insight→Action), and voice/tone; detects out-of-scope requests (FAQs, comparison tables); surfaces conflicts between user brief and audience needs. Writes approved outline to .plans/content/<slug>-outline.md for foundry:creator to execute. Use when starting a blog post, Marp slide deck, social thread, talk abstract, or lightning talk.
distill
One-time snapshot extracting patterns from work history and accumulated lessons, distills into concrete improvements — new agent/skill suggestions, memory pruning, consolidating lessons into rules/agent updates, or performing bin/ extraction from /audit --efficiency candidates. Roster boundary analysis → /foundry:audit agents (Check 34).
humanizer
Strip AI-writing tells from prose destined for humans — docs, PR/commit bodies, reports, release notes, blog posts, Slack/email drafts. Removes LLM-vocabulary clichés (delve, boasts, testament, underscore, robust, tapestry...), banned constructions (not just X but Y, rule-of-three triads, "-ing" superficial-analysis clauses, vague-attribution weasel words), and formatting tells (title-case headings, mechanical bolding, em-dash overuse, curly quotes, bare-bullet inline-header lists). TRIGGER when: user asks to humanize/polish/de-AI a piece of text or file; before finalizing a substantial human-facing prose artifact drafted as part of the current task (docs, PR/commit body, report, blog post, release notes, external message) — self-review pass, best-effort model-initiated, not a guaranteed intercept. SKIP when: output is a terse conversational chat reply, code, JSON/YAML/config, a machine-parsed agent envelope ("Return ONLY:"), or the target is an ultra-caveman-tier handover file (`.temp/`, inter-agent prose pe
profile
Session clock-time AND token/cost analyzer. Reads the foundry plugin's timings.jsonl and invocations.jsonl logs (written by task-log.js) for wall-time, plus Claude Code transcripts (~/.claude/projects/**, main-loop + subagent files) for token usage and USD cost, and merges both into one per-session and per-skill report — local-tool vs subagent-spawn vs Skill vs AskUserQuestion idle vs main-loop reasoning residual time, and main-loop vs subagent spend by model tier. Useful for answering "why did /oss:resolve run 30 minutes?", "what did this session cost?", or "which skill burns the most tokens?". Pure log/transcript read — no instrumentation, no skill edits, no LLM calls. TRIGGER when: user asks where wall-clock time OR tokens/cost go during a skill/session, why a skill is slow or expensive, what dominates total runtime or spend, or wants a per-skill rollup over a recent window; phrases: "where does time go", "why so slow", "what did this cost", "token spend", "why so expensive", "profile last session", "clock
session
Session state that outlives a context reset — `dump` sweeps the live conversation and writes a compact handover doc (goal, decisions + why, lessons, standing instructions, files-touched table, outstanding items, next step), then prints `/clear`; the `session-restore.js` SessionStart hook re-injects it automatically. `park` stashes a diverging idea mid-session without derailing; `sweep` audits the conversation for unlanded work. TRIGGER when: user says "dump the session", "handover before clear", "save state before clearing", "carry this over", "I want to clear but keep the plan", "park this for later", "what did we defer", "anything unfinished before I close". SKIP: surviving auto-compact at 85% (that is the skill contract in `.temp/state/skill-contract.md` per `compaction.md`, written by the running skill); reviving a *finished* conversation (Claude Code native `/resume`).
resolve
OSS maintainer fast-close workflow for GitHub PRs. Three phases: (1) PR intelligence — reads full thread, linked issues, PR body to synthesize contribution motivation and classify every comment into action items; (2) conflict resolution — checks out PR branch (fork-aware via gh pr checkout), merges BASE into it, resolves conflicts semantically using contributor's intent as priority lens; (3) implements each action item as separate attributed commit via Codex, pushes back to contributor's fork. Supports three source modes: pr (live GitHub comments only), report (latest /review report findings as action items, no GitHub re-fetch), and pr + report (both sources aggregated and deduplicated in one pass). Also accepts bare comment text for single-comment dispatch. NOT for reply drafting to /oss:analyse findings (use /oss:analyse --reply (requires `oss` plugin)). NOT for code diff review of PR changes (use /oss:review). NOT for release preparation (use /oss:release). NOT for fixing local bugs unrelated to a PR (use
fortify
Systematic ablation study runner. After research:run finds improvements, fortify identifies component candidates from git diff + diary, creates isolated git worktrees per ablation (main repo never modified), runs metric+guard in each worktree, ranks component importance, and optionally generates reviewer Q&A calibrated to a target venue.
judge
Research-supervisor review of program.md — validates experimental methodology (hypothesis clarity, measurement validity, control adequacy, scope, strategy fit), emits APPROVED / NEEDS-REVISION / BLOCKED verdict before expensive run loop.
retro
Post-run retrospective: reads .experiments/ JSONL, computes Wilcoxon significance, detects dead iterations, flags suspicious jumps, generates next-hypothesis queue for --hypothesis flag.
run
Sustained metric-improvement loop with atomic commits, auto-rollback, and experiment logging. Iterates with specialist agents, commits atomically, auto-rolls back on regression. Accepts a program.md file path. Supports --resume, --team, --colab, --codex, --researcher, --architect, --journal, --hypothesis.
sweep
Non-interactive end-to-end pipeline — auto-configure program.md (accept defaults), run judge+refine loop (up to 3 iterations), then run the campaign. Single command from goal to result.
topic
Research State of the Art (SOTA) literature for an Artificial Intelligence / Machine Learning (AI/ML) topic, method, or architecture. Finds relevant papers, builds a comparison table, recommends the best implementation strategy for the current codebase, and optionally produces a phased implementation plan mapped to the codebase. Owns broad SOTA search end-to-end via foundry:web-explorer; delegates codebase mapping to foundry:solution-architect.
verify
Paper-vs-code consistency audit. After research:scientist implements a method from a paper, verify the implementation matches paper claims across five dimensions — formula matching [F], hyperparameter parity [H], eval protocol [E], notation consistency [N], and citation chain [C]. Reads paper (PDF path / arXiv URL / pasted text), maps claims to codebase, emits verification table with match status and severity.
integration
Codemap integration: audit|plan|apply|sync|demo; skip query/index rebuilds.
rename-refs
`$codemap-py:rename-refs`: rename Python names; skip non-Python/unbuilt/local/grep/split/pkg-dir.
scan-codebase
`$codemap-py:scan-codebase [flags]` only: Python index; never auto-invoke; skip query/integration.
test-impact
`$codemap-py:test-impact <qname> [--no-mocks]`: affected tests; skip caller/dependency query/exec.
audit
Audit Codex configuration/workflow drift; emit ranked gaps and measurable gates.
calibrate
Calibrate skills/role cards for leaks/gaps with recall, precision, and confidence-accuracy checks.
investigate
Investigate code debugging and root-cause narrowing; use measurable gates before fixes.
manage
Minimal codex-native management loop. Use to create, update, or remove Codex agents/skills/config entries with guardrails.
analyse
Analyze issue/PR/problem before implementation; produce source-backed findings and measurable gates.
release
Minimal codex-native release loop. Use for SemVer-aware release readiness with measurable gates and artifact output.
kaggle
Generate or extend grounded Kaggle competition notebooks as Jupytext `# %%` Python scripts. Use for full training notebooks, EDA-only notebooks, checkpoint-based inference notebooks, or resuming an existing Kaggle script across classification, regression, segmentation, detection, tabular, time-series, point-cloud, and mixed-modality tasks.
code-remediate
Apply selected code-review fixes; rerun gates/report gaps; PR +review uses latest matching artifact.
code-review
Review local diffs/PRs with scope gates, specialists, and JSON artifact; fix via code-remediate.
develop
Implement changes with a linear plan-build-verify workflow and measurable quality gates.
optimize
Minimal codex-native optimization loop. Use for metric-driven improvements with guardrails and measurable gates.
research
Minimal codex-native research loop. Use for docs/papers/state-of-the-art scan with source-backed recommendations.
sync
Dry-run-first Codex Rig installation drift and update workflow. Use to inspect the active plugin cache, refresh its GitHub marketplace, or reinstall the current plugin while coordinating separately managed agent shims.
agent-shims
Safely manage Codex Rig role-agent shims: doctor, status, install, or remove; one action only.
debrief-coding
Telemetry report: `$codemap-py:debrief-coding [flags]`; skip integration/index/query.
change-analysis
Analyze issue/PR/problem before implementation; produce source-backed findings and measurable gates.
query-code
Query Codemap.
cancel
Request cancellation of a running detached Codex bridge job.
result
Read a completed detached Codex bridge job's compact result.
review
Request a read-only adversarial review from Claude Code through the sandbox-external bridge.
setup
Diagnose Claude Code availability and the bridge MCP bridge from Codex.
implement
Ask Claude Code to implement one bounded write-capable change through the sandbox-external bridge.
advise
Ask Claude Code a read-only question from Codex through the sandbox-external bridge.
status
Read a detached Codex bridge job's current state.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.