Idea Pipeline

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 0448e87653f9 · 14 Oct 2026Report an issue or request a re-scan

• Publisheraaronjmars GitHub organizationOwner of the repository this skill is read from
• Source folderaaronjmars/aeon/skills/idea-pipelineThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict0448e87653f9A new audit runs when the source changes
• Repository statusNot archivedPushed today
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Execution-gap audit - cross-references the startup idea backlog against shipped skills, prototypes, and cross-repo PRs, surfacing the top 3 ideas to build next by narrative and operator fit.

---
name: idea-pipeline
description: Execution-gap audit - cross-references the startup idea backlog against shipped skills, prototypes, and cross-repo PRs, surfacing the top 3 ideas to build next by narrative and operator fit.
metadata:
  category: productivity
  var: ""
  tags:
    - meta
    - creative
---
> **${var}** — Optional theme filter (e.g. "crypto", "AI agents", "consumer"). If empty, scans all ideas. A `pick:<id|name>` value (from the "build next?" force-reply — e.g. `pick:2` or `pick:Onchain reputation`) instead marks that idea as chosen-to-build in the backlog and ends, skipping the audit — see step 0. `offer:<owner/repo or issue-url>` directly offers a confirmed owned target through the same Telegram reply boundary, also ending before the audit.

Today is ${today}. Read `memory/MEMORY.md` before starting. If `soul/SOUL.md` + `soul/STYLE.md` exist and are populated, read them to ground "operator fit" scoring; otherwise score on the idea's general buildability and timing alone.

## Why this skill exists

`idea-forge validate` evaluates ideas. Nothing tracks execution. Backlogs of dozens of ideas accumulate — some validated, most unscreened — with zero visibility into which ones have been acted on vs which are rotting. This skill gives that view: pipeline size, execution rate, and the 3 ideas closest to being buildable right now.

## Steps

### 0. Force-reply interception — `pick:<idea>` / `offer:<target>` (run FIRST, before anything else)

If `${var}` starts with `offer:`, strip and trim the remainder. Accept only `owner/repo` or `https://github.com/owner/repo/issues/N`, normalize it to `owner/repo`, and require `gh api "repos/$repo" --jq '.permissions.push // false'` to return `true`. Invalid, inaccessible, or API-failed targets get a plain rejection notification and end without a force reply. For a confirmed target, execute this exact command with Bash. Describing or printing the command is not delivery:

```bash
./notify "Which owned repository or issue should Aeon Engineer use? Reply with ${target}." \
  --force-reply --placeholder "${target}" \
  --context "dev-loop::ship"
```

After the command exits zero, require at least one non-empty JSON payload under `${AEON_PENDING_DIR}/notify-queue/` **and** that payload's `.reply_markup.force_reply == true`. A queued payload alone isn't enough — `notify.sh` queues one even when the inbound Messages workflow is disabled, but in that case sends the prompt as plain text (`reply_markup:null`) with no reply routing, so the operator's answer would never come back to this skill. If the command fails, the payload is absent, or `force_reply` isn't `true`, end with `FORCE_REPLY_MISSING: dev-loop::ship target=<target>` and do not claim the prompt was offered. Only after both checks pass, log `FORCE_REPLY_OFFERED: dev-loop::ship target=<target>` under `### idea-pipeline`, then end. This is an explicit operator-invoked producer path and still does not dispatch the chain until the operator replies.

Otherwise, if `${var}` starts with `pick:`, this run is the operator answering the "which idea to build next?" force-reply — do **not** run the normal audit. Handle it and end:

1. Strip the prefix: `sel="${var#pick:}"`, then trim surrounding whitespace. The remainder may contain colons/spaces — keep them.
2. If `sel` is empty, send a plain re-ask (no force-reply) and end: `./notify "Which idea should I mark as next to build? Reply with its name or backlog number."`
3. Read the shared backlog `memory/topics/startup-ideas.md`. If it's missing or has no idea rows, `./notify "No idea backlog yet — nothing to mark. Run idea-forge generate to fill it first."` and end.
4. Resolve `sel` to exactly one idea row in the table (columns `| date | name | one-liner | fit | T+F+E |`):
   - **By name (preferred):** case-insensitive exact match on the `name` cell; else fuzzy — the row whose name shares the most significant words with `sel`, or where `sel` is a substring of the name (or vice-versa). Require one clear best match.
   - **By number:** if `sel` is a bare integer N and no name matches, take the Nth data row (1-based, in file order).
   - If nothing matches, or two rows tie with no clear winner, send a plain re-ask listing 3–5 candidate names and end: `./notify "Couldn't find an idea matching \"<sel>\". Reply with the exact name or backlog number. Candidates: <name1>, <name2>, <name3>."`
5. **Mark it chosen-to-build** — the shared marking convention (identical in idea-forge): append ` ✓ selected ${today}` to the end of that row's `name` cell, keeping the table pipes intact. If the cell already carries a `✓ selected` marker, leave it (idempotent) — it's already queued.
6. **Do not try to infer a GitHub target from the row.** The backlog's row schema (columns `| date | name | one-liner | fit | T+F+E |`) never carries a repo or issue reference, so a per-row target lookup here would never match a real row. `offer:` (step 0) is the only path from a marked idea to a dev-loop dispatch — explicit and push-permission-gated on purpose.
7. Confirm with a short `./notify` (keep it clean — no `test`/`trace`/`ping`/`debug` substrings): `./notify "Marked \"<idea name>\" as next to build — flagged in the backlog. Run /feature or /deploy-prototype on it when you're ready, or reply with: offer:<owner/repo> to have Aeon Engineer start on it directly."` Do not auto-dispatch any skill — marking chosen is the safe action.
8. Log to `memory/logs/${today}.md` under a `### idea-pipeline` heading: `- IDEA_PIPELINE_PICK: marked "<idea name>" as chosen-to-build (from a pick: reply)`.
9. **End the run.** Do not proceed to step 1 or run the audit.

### 1. Load the idea backlog

Read `memory/topics/startup-ideas.md`. If it doesn't exist, log `IDEA_PIPELINE_SKIP: no backlog at memory/topics/startup-ideas.md` and stop — there's nothing to audit.

Parse the ideas table: extract name, one-liner, category/vertical, and date added for each idea. Total = N_total.

### 2. Load screening res

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/aaronjmars/aeon
git -C aeon checkout 0448e87653f9

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source 0448e87653f9

Questions about Idea Pipeline

• github.com/aaronjmars/aeon/tree/main/skills/idea-pipeline — the audited source at commit 0448e87653f9 and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology