agentleFS
veraetogrex-portfolioveraetogrex-portfolio/solo-sdd/skills/blockers/SKILL.md

blockers

Skill0 starsChanged yesterdayMITView on GitHub

Use only when the user explicitly invokes /blockers - "move the blockers into a separate change", "write all blockers out into a separate change", "found outside the change, a separate change is needed", "move it into a separate change and go on".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every new one: the rest of the artifacts (verification.md, deltas or Specs: none) by the "Writing rules" of spec-plan, then solo-sdd …

    line 21
  2. Very specific:

    A project without a solo-sdd/ tree: If it has openspec/ instead, name the next step solo-sdd import openspec in the report.

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

blockers: blockers and findings into separate changes, the work goes on

Argument (optional): what exactly to move out. Without an argument collect everything yourself: blockers and findings beyond the current work from this session, the "Not Verified" section in verification.md of the current change, the "found outside the change" items from reports.

Order

  1. List. For every item: what blocks or what was found, what we wait for (access, the user's decision, data, an external service), who can lift it.
  2. Split.
    • A blocker: the work exists but waits for an external condition.
    • A finding: work beyond the current specification.
  3. A project with a solo-sdd/ tree. Take the number and name by the pattern of the neighbouring changes (solo-sdd list --json, the next free number); create each new change with solo-sdd new <id>.
    • Blockers of the current change: one new change <number>-<topic>-blockers: proposal.md (what we wait for and why), tasks.md (steps after the condition is lifted), a WAITING file with the condition, a line in docs/waiting.md. A link to it in verification.md of the current change.
    • Findings: one change per independent topic: proposal.md and tasks.md, without WAITING.
    • Every new one: the rest of the artifacts (verification.md, deltas or Specs: none) by the "Writing rules" of spec-plan, then solo-sdd validate <id>.
  4. A project without a solo-sdd/ tree. If it has openspec/ instead, name the next step solo-sdd import openspec in the report. Blockers go into docs/waiting.md, findings into docs/backlog.md. No file: create it.
  5. Commit. The new artifacts in a separate commit by the project rules (/ship).
  6. Continuing. Change the current change only with links. If you were running it, continue from the next item of tasks.md without stopping.

Report (in the user's language)

ItemBlocker or findingWhere it wentLift condition

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.