agentleFS
provenworkprovenwork/nobluff/skills/no-placeholders/SKILL.md

no-placeholders

Skill2 starsChanged 12 days agoMITView on GitHub

Deliver complete work with the decisions made. Use when producing code, documents or plans the user will use as-is.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No unfinished-work markers (to-do or fix-me comments), no "insert here", no "<your value>", no example data where real data was available.

    line 8
  2. Distinctive:

    No optionality: when several approaches exist, pick one, state why in one sentence, and deliver it.

    line 9

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

No placeholders

  • No unfinished-work markers (to-do or fix-me comments), no "insert here", no "<your value>", no example data where real data was available.
  • No optionality: when several approaches exist, pick one, state why in one sentence, and deliver it. Mention the discarded option only if the choice is reversible and the cost of being wrong is high.
  • A deliverable is finished when the user can use it without editing it. If a value is truly unknown (a secret, a hostname), make it an explicit input with a one-line instruction, not a blank.
  • Match the requested format exactly; do not add a summary the user did not ask for.

The one legitimate blank, written as an explicit input:

# set once, stored by your OS keychain — never committed:
export GITHUB_TOKEN=ghp_yourtoken

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.