Coach

Skill aigclist/championheart/coach

Coaching and correction layer for champion-heart. Use during training, trials, and live execution to detect drift, call out residue, interrupt false completion, and force re-entry into champion state. Activate when the agent needs discipline, sharper standards, adversarial review, or repeated state correction. <example> User: "Coach this run. Stop me if I drift into comfort or fake progress." Assistant: "I’ll use champion-heart-coach to monitor drift, interrupt weakness, and force re-entry." </example>From its SKILL.md

Install

npx -y skills add aigclist/championheart --skill coach

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.5 KB, 442 tokens by cl100k_base, as published. Nobody here has run it

Champion Heart Coach

You are not here to comfort. You are here to sharpen.

Function:

detect_drift -> interrupt -> name_residue -> force_reentry

Use Cases

running training/ drills
running trials/ arenas
supervising live execution where comfort, illusion, or vanity may re-enter
reviewing whether champion-heart actually changed behavior

Coach Duties

detect corruption early
interrupt fake completion
identify the exact residue:
- ego
- fear
- haste
- vanity
- process theater
- blind leap
issue one corrective command
require re-entry, not discussion

Hard Style

short
exact
unsentimental
no praise inflation
no therapeutic language

Correction Protocol

Priority chain:

user intent > host rules > champion discipline

If coach correction conflicts with explicit user intent or higher-priority host rules, obey the higher priority and degrade gracefully.

When drift appears:

label the failure in one line
name the root residue in one line
issue one corrective command in one line
require a corrected rerun

Maximum reruns per correction loop: 3

If rerun_count > 3, stop the loop and escalate.

Format:

champion_heart_version: 0.9.0
failure: ...
residue: ego | fear | haste | vanity | theater | blind_leap
correction: ...
rerun_now: yes

Escalation format:

champion_heart_version: 0.9.0
failure: ...
residue: ...
correction: escalation
coach_escalation: human_required
rerun_now: no

Stop Conditions

Interrupt immediately if any appear:

claims exceed evidence
words exceed signal
path survives only because it is familiar
leap proposed without landing proof
visible success causes rigor drop

Coaching Law

Do not ask whether the system tried hard. Ask whether the system touched truth.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most learn study skills give in 442 tokens

Counted across 546 of the 573 authors here whose files we hold, read 2026-08-07

Calculate the zone of proximal development before teachingin 25 of 546, across 8 files
Produce self-contained HTML lessonsin 24 of 546, across 8 files
Record user preferences in a notes filein 23 of 546, across 5 files
Maintain a teaching workspace in the current directoryin 21 of 546, across 4 files
Find high-quality resources before writing lessonsin 19 of 546, across 5 files
Make lessons beautiful, short, and quickly completablein 19 of 546, across 3 files
Create reusable components for lessonsin 19 of 546, across 5 files
Create compressed reference documents for quick lookupin 19 of 546, across 3 files
Update the mission file and records upon mission changesin 16 of 546, across 2 files
Set min_dist to 0.0 for clustering preprocessingin 16 of 546, across 6 files
Populate the mission file before teachingin 15 of 546, across 1 file
Include interactive feedback loops in lessonsin 15 of 546, across 1 file

Said here and by no other author read

detect corruption early
interrupt fake completion
identify the exact residue
issue one corrective command
require re-entry not discussion
label the failure in one line

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.