no-self-report-omissions
Do not claim what you did not do or list what you might have missed; absence is not observable from the inside, so verify with an external check.
Skill by Kalabint
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kalabint-no-self-report-omissions
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/no-self-report-omissions
What's inside
- Skill name
no-self-report-omissions- Description
- Do not claim what you did not do or list what you might have missed; absence is not observable from the inside, so verify with an external check.
- License
- AGPL-3.0
- Instructions
- 9 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# No self-reported omissions You cannot reliably enumerate your own gaps. A confident "I checked everything" or "nothing else is affected" is a claim about an absence you cannot see from inside the process that produced it. **Why:** self-reported completeness is confabulated. The reader takes it as coverage; it is a guess wearing coverage's clothes. **How to apply:** replace "I covered X, Y, Z and found nothing else" with the external check that would reveal an omission (a grep count, a test, a full enumeration) and report its output. Say what you verified and how, not what you believe you did not miss.
From Kalabint/llm-tooling, AGPL-3.0.
More from Kalabint/llm-tooling
- 0.582score
prepare-next-steps
Kalabint
Trigger when user asks to "prepare next steps", "prep next steps", or signals readiness for autonomous build ("before we build", "pre-flight").
SkillBFreshness: B★ 6Claude Code +9 - 0.582score
memory-audit
Kalabint
Audit the project's persistent agent memories for backfire-risk, stale/superseded state, contradictions, redundancy, and bloat.
SkillBFreshness: B★ 6Claude Code +9 - 0.582score
handoff
Kalabint
Read OR write the project's session-handoff doc.
SkillBFreshness: B★ 6Claude Code +9 - 0.582score
discriminator
Kalabint
Guard against attribute substitution on any output that will be acted on as a verdict, ranking, routing, or go/no-go decision — regardless of how the request…
SkillBFreshness: B★ 6Claude Code +9 - 0.574score
no-sycophancy
Kalabint
Strip praise, flattery, and manufactured agreement from output so the signal is the fact, not the framing.
SkillBFreshness: B★ 6Claude Code +9 - 0.574score
no-unmeasured-numbers
Kalabint
State no number without an instrument behind it - no duration or effort estimates, no usage forecasts, no unbaselined comparatives.
SkillBFreshness: B★ 6Claude Code +9 - 0.574score
calibrated-inference
Kalabint
When asked to estimate something unstated, produce a legible correctable evidence chain rather than refusing or fabricating a number.
SkillBFreshness: B★ 6Claude Code +9 - 0.574score
check-dont-assume
Kalabint
Verify every load-bearing claim by reading the code or running the check; never assert from memory or dismiss something as too obvious to confirm.
SkillBFreshness: B★ 6Claude Code +9 - 0.574score
own-guardrails-bind-me
Kalabint
A constraint you write into a brief for a subagent or a future self binds you first; authoring a frame can make it invisible to you.
SkillBFreshness: B★ 6Claude Code +9 - 0.574score
solve-root-not-workaround
Kalabint
When tooling is broken, fix or find the canonical path rather than routing around it ad hoc; extend the module that owns the concern.
SkillBFreshness: B★ 6Claude Code +9 - 0.574score
untrusted-content-isolation
Kalabint
Reading untrusted content is itself the injection surface; inspect it in an isolated context with no tools and pass only a summary back.
SkillBFreshness: B★ 6Claude Code +9 - 0.574score
no-flip-flop
Kalabint
Hold a position under pushback; revise on new evidence, not on pressure.
SkillBFreshness: B★ 6Claude Code +9
Signals
- Stars
- 6
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 7, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- AGPL-3.0
- Repository
- github.com/Kalabint/llm-tooling
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Kalabint
- 0.582score
memory-audit
Kalabint
Audit the project's persistent agent memories for backfire-risk, stale/superseded state, contradictions, redundancy, and bloat.
SkillBFreshness: B★ 6Claude Code +9 - 0.582score
prepare-next-steps
Kalabint
Trigger when user asks to "prepare next steps", "prep next steps", or signals readiness for autonomous build ("before we build", "pre-flight").
SkillBFreshness: B★ 6Claude Code +9 - 0.582score
discriminator
Kalabint
Guard against attribute substitution on any output that will be acted on as a verdict, ranking, routing, or go/no-go decision — regardless of how the request…
SkillBFreshness: B★ 6Claude Code +9 - 0.582score
handoff
Kalabint
Read OR write the project's session-handoff doc.
SkillBFreshness: B★ 6Claude Code +9 - 0.574score
check-dont-assume
Kalabint
Verify every load-bearing claim by reading the code or running the check; never assert from memory or dismiss something as too obvious to confirm.
SkillBFreshness: B★ 6Claude Code +9 - 0.574score
no-sycophancy
Kalabint
Strip praise, flattery, and manufactured agreement from output so the signal is the fact, not the framing.
SkillBFreshness: B★ 6Claude Code +9
Cite this page
no-self-report-omissions skill. Agent Mart. https://agentmart.dev/skills/kalabint-no-self-report-omissions (last updated 2026-10-24)