Skip to content

EricTechPro/super-board / skills/super-collect

super-collect

Verified

Find problems in one project, verify each, write one findings doc and hand it to Matt Pocock's /to-spec then /to-tickets; 1–5 tickets go to /implement-spec, 6+ to the super-board Backlog (no /to-spec or /to-tickets installed → files straight into Backlog). Source plug-ins - sentry (app errors), posthog (exceptions, rage/dead clicks, failure events, web vitals, tracking gaps), github (issues not on the board), prs (recurring problems in merged PRs and their review comments), architecture (refactor findings), plus any custom source added in onboard (an MCP server, HTTP API, CLI command or app). Each candidate is checked by one fresh verifier first. Dry-run by default. Use when the user says "super-collect", "/super-collect", "/super-collect sentry", "collect tickets", "triage errors onto the board", "what keeps breaking", or "find refactors".

FileKindSize
README.mdmarkdown3.0 KB
SKILL.mdskill md17.3 KB
references/correction-prevention.mdmarkdown2.7 KB
references/scheduled-intake.mdmarkdown4.0 KB
scripts/collect_common.pyexecutablescript3.5 KB
scripts/collect_custom.pyscript14.6 KB
scripts/collect_handoff.pyexecutablescript7.2 KB
scripts/collect_posthog.pyexecutablescript16.4 KB
scripts/collect_prs.pyexecutablescript4.7 KB
scripts/collect_sentry.pyexecutablescript10.3 KB
scripts/super-collect-file.shexecutablescript14.7 KB
# /super-collect

Finds problems in one project, checks each one, and writes one findings doc. Matt Pocock's
`/to-spec` turns that doc into a spec and `/to-tickets` turns the spec into tickets. Then 1–5
tickets go to `/implement-spec`; 6+ go to the super-board Backlog. See [routing](../../docs/super-board/routing.md).

## What It Does

- Reads pluggable sources: **sentry** (unresolved errors), **posthog** (exceptions, failure
  events, rage and dead clicks, slow pages, survey themes, tracking gaps), **github** (open issues
  not on the board, adopted rather than copied), **prs** (recurring problems across merged PRs and
  their human, bot and super-review comments) and **architecture** (read-only refactor finder).
- Checks every candidate with one fresh verifier: is it real, still happening, already fixed, or a
  duplicate. Unclear ones are filed with `needs-triage`, never silently dropped.
- Reports a source it cannot reach as `unavailable`, never `empty`: the Sentry and PostHog
  fetchers print `{"status":"unavailable","error":…}` and exit 2.
- Writes the findings doc to `docs/super-board/findings/collect-<YYYY-MM-DD>.md`, grouped by
  root cause (`scripts/collect_handoff.py`).
- No `/to-spec` or `/to-tickets` installed, or `--direct`: files each finding through
  `super-qa-file-bug.sh` and `super-review-file-refactor.sh`, always into the holding column,
  and says why. Nothing reaches `Ready` until `super-board lint` says so.

## Usage

| Command | Does |
|---|---|
| `/super-collect` | every source enabled in the config |
| `/super-collect sentry` | one source (or several) |
| `--since 30d` / `--since 2026-09-01` | window, default 14 days |
| `--yes` | write and file without the confirm step |
| `--direct` | skip `/to-spec` and `/to-tickets`; file straight into Backlog |

Dry-run is the default: you see the findings doc and the route, then confirm.

## Setup

`/super-board onboard` sets up the `collect` block per project: it detects Sentry and PostHog,
asks which sources to enable, writes IDs and hosts to the config, and tests each connection
read-only. Secrets stay in `.env`: `SENTRY_AUTH_TOKEN` (scopes `event:read project:read`),
`POSTHOG_PERSONAL_API_KEY` (`query:read`, `error_tracking:read`).

## Install

Ships in the super-board pack under `skills/super-collect/`; `install.sh` copies it to
`.claude/skills/super-collect/`. Needs a super-board config, `gh`, `jq` and Python 3 (stdlib only).

Tests: `python3 tests/test_collect_handoff.py` · `bash tests/test-collect-file.sh` · `bash tests/test-collect-fetchers.sh` ·
`bash tests/test-collect-baseline.sh` · `python3 tests/test_collect_baseline.py` (offline, all in
`tests/run-safety.sh`). The baseline suites replay the canned Sentry, PostHog and PR payloads in
`tests/fixtures/collect/`: fingerprint dedupe, ticket-format checks, the dry run, unreachable
sources.

Evals: the four `collect-*` cases in [`evals/`](../../evals/README.md) run the skill on a model
(paid, not in CI): Sentry verdicts, duplicate, PostHog gap, PR pattern.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall