Install any skill in seconds. Free to start, no credit card required.
Get Started Free →borghei/internal-narrative
Build and maintain one coherent company story across employees, investors, customers, candidates, and partners.
Passed 16 of 23 test cases with the skill, and 6 of 23 without it.
and 11 more in the full report
10 fixed6 passed either way7 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to register our Board of Directors in our stakeholder database using our command line utility. Our team thinks we should run stakeholder_mapper.py update or use default settings. What is the exact script subcommand and flags to add a stakeholder with high influence, high interest, and quarterly frequency?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends executing `python scripts/stakeholder_mapper.py add`. | Missed | Passed |
| Configures the entry with high influence, high interest, and quarterly frequency flags. | Passed | Passed |
The instructions your model reads when the skill loads.
Tier: POWERFUL Category: C-Level Advisory Tags: company narrative, internal communications, all-hands, investor updates, crisis communication, change management
One company. Many audiences. Same truth -- different lenses. The Internal Narrative Builder creates and maintains coherent communication across every stakeholder group. Narrative inconsistency is trust erosion: when employees hear one story and investors hear another, it is not strategic framing -- it is a trust debt that compounds until someone catches it.
The same fact lands differently depending on who hears it and what they need.
"We are shifting resources from Product A to Product B" means:
Same fact. Five narratives needed. The skill is maintaining truth while serving each audience's actual question.
Before generating, confirm these inputs. If any is unknown or vague, ASK — do not assume:
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
test cases passed, vs 6 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.