agentleFS
fzfcleefzfclee/consulting-skills/skills/fifteen-percent-solutions/SKILL.md

fifteen-percent-solutions

Skill6 starsChanged 4 months agoApache-2.0View on GitHub

Use when the user needs immediate controllable next actions inside limited authority, resources, or certainty. Use when applying 15% Solutions, small controllable action, low-regret next step, agency boundary, or next-72-hour action planning.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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. Distinctive:

    Use this skill to find actions the user can take now without waiting for full authority, perfect certainty, or broad alignment.

    line 9
  2. Very specific:

    If an input is missing, mark it as missing, state the assumption used, and add a validation action.

    line 27
  3. Very specific:

    Do not use when a high-risk action requires formal approval, legal review, compliance clearance, or irreversible commitment.

    line 31
  4. Distinctive:

    Do not recommend manipulation, pressure tactics, or hidden escalation.

    line 75
  5. Distinctive:

    Avoid over-investing before the validation signal appears.

    line 77
  6. Distinctive:

    Keep instructions concrete: who, what, when, and what response to look for.

    line 78

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Fifteen Percent Solutions

Use this skill to find actions the user can take now without waiting for full authority, perfect certainty, or broad alignment.

Method Notes

  • A 15% solution is a small action inside the user's current control boundary.
  • It should be meaningful enough to create evidence or movement, not just busy work.
  • It is especially useful after diagnosis shows the full outcome depends on other people.

Required Inputs

Collect or infer these inputs before execution:

  • desired outcome
  • user's role, authority, relationships, and constraints
  • blockers outside the user's control
  • available time, access, and resources
  • risk tolerance

If an input is missing, mark it as missing, state the assumption used, and add a validation action.

When Not To Use

Do not use when a high-risk action requires formal approval, legal review, compliance clearance, or irreversible commitment. Use risk-matrix, raci-matrix, or communications-plan first.

Step-by-Step Execution

StepRequired inputHow to executeOutput
State the desired movementOutcome, current blockage.Define what progress would look like in the next few days.Near-term progress target.
Map control boundaryRole, authority, access, constraints.Separate what the user controls, influences, and cannot control.Control boundary map.
Generate small actionsControl boundary, available resources.List actions that require no new permission or only low-risk informal alignment.Candidate 15% actions.
Screen for usefulness and riskCandidate actions, risk tolerance, stakeholder context.Keep actions that create evidence, open a door, reduce ambiguity, or build trust. Remove symbolic busy work.Shortlisted actions.
Choose first actionShortlist, timing, expected signal.Select 1-3 actions for the next 24-72 hours.Immediate action plan.
Define evidence signalAction, expected response, decision gate.State what result means continue, adjust, or stop.Validation signal.

Output Template

### 1. Near-Term Progress Target
- Desired movement in the next 24-72 hours:
- Current blocker:

### 2. Control Boundary
| Area | Inside my control | I can influence | Outside my control |
|---|---|---|---|
|  |  |  |  |

### 3. Candidate 15% Actions
| Action | Why it is within control | Expected signal | Risk level | Keep / drop |
|---|---|---|---|---|
|  |  |  | low / medium / high |  |

### 4. Recommended First Moves
1.
2.
3.

### 5. Decision Gate
- Continue if:
- Adjust if:
- Stop or escalate if:

Quality Gate

  • The action must be genuinely within the user's current control or low-risk influence.
  • Do not recommend manipulation, pressure tactics, or hidden escalation.
  • The action should generate evidence, trust, access, or clarity.
  • Avoid over-investing before the validation signal appears.
  • Keep instructions concrete: who, what, when, and what response to look for.

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.